# Introduction Access the world's most powerful AI media enhancement APIs designed for true scale and automation. Our enhancement models are used by 3M+ users worldwide and trusted by teams at Google, Tesla, Nike, and Nvidia as their last-mile solution for improving the quality of their images and videos. All of our AI models are developed in-house by our team of PhD researchers in Dallas, Texas. Topaz AI models focus on unparalleled: * **Quality**: Industry-defining quality fit for professional use cases ranging from Hollywood to AAA game studios to pro photographers. * **Fidelity**: Preserve the original details and identities in source media with Topaz Labs models better than any other offering in the industry. * **Efficiency**: Low per-unit cost with maximum speed for enhancing thousands or even millions of files at a time. ### What Makes the Topaz Labs API Unique? Automation requires a different way of thinking about enhancement. For years, creatives have had access to the best interactive applications to refine their images and videos β€” manually adjusting parameters until they hit that sweet spot. At scale, there isn't room for that. You need a solution that moves as fast as you do without sacrificing quality. Topaz models have default, automatic settings, which can produce the highest quality outcome with no manual tuning. ### Model Types Topaz Labs offers three AI model familes: * **Precision**: Models designed to improve quality while preserving original source characteristics. * **Generative**: Models designed to improve quality by intelligently adding detail and texture while preserving artistic intent. * **Creative**: Models designed to add new levels of detail that can transform objects, identity, and stylization. Additionally, we offer various other families of models, such as Sharpen, Denoise, Utilities, and more. ### Image Models Our image enhancement APIs offer world-class upscaling, face recovery, sharpening, denoising, removal, and more. | Family | Capability | | -------------------------------------------------------- | --------------------------- | | [`Gigapixel`](/image-models/gigapixel) | Precision Upscaling | | [`Wonder`](/image-models/wonder) | Generative Upscaling | | [`Bloom`](/image-models/bloom) | Creative Upscaling | | [`Sharpen`](/image-models/removal-and-cleanup/sharpen) | Sharpening | | [`Denoise`](/image-models/denoise) | Denoising | | [`Removal & Cleanup`](/image-models/removal-and-cleanup) | Inpainting & Object Removal | | [`Color & Lighting`](/image-models/color-and-lighting) | Color & Lighting Correction | ### Video Models Our video enhancement APIs offer world-class upscaling, frame interpolation, denoising, compression recovery, and more. | Family | Capability | | ---------------------------------------------------------- | ------------------------------------------------ | | [`Proteus`](/video-models/proteus) | Precision Upscaling | | [`Starlight`](/video-models/starlight) | Generative Upscaling | | [`Astra`](/video-models/astra) | Creative Upscaling | | [`Denoise`](/video-models/denoise) | Denoising | | [`Frame Interpolation`](/video-models/frame-interpolation) | Motion Smoothing | | [`Video Utilities`](/video-models/video-utilities) | Compression Recovery, Detail Enhancement, & More | ### Getting Started * [Image API Quickstart](/getting-started/quickstart) * [Video API Quickstart](/getting-started/video-api-quickstart) * [Pricing](/getting-started/tier-pricing) * [Credit Calculator](https://developer.topazlabs.com/credit-calculator) For questions, reach out to . For enterprise inquiries, contact . # Image API Quickstart In this example, we’ll be using one of our most popular image models, Standard 2. Before we proceed, you need to create an [API key](https://account.topazlabs.com/manage-api). This key will be used to authenticate your requests to the Topaz Labs API.
How do I get my API key? In order to get access to the API, you'll need to [log into](http://topazlabs.com/account) your Topaz Labs account and create your unique API key. If you don't have an account, please follow the link [here](https://topazlabs.com/wp-login.php?action=register) to register.
1. Log into your Topaz Labs account from our [website](https://topazlabs.com/my-account/) 2. Navigate to the **API Keys** section in your account portal, enter a name, and click **Create** 3. Copy your API key (displayed at the top of the screen) and store it in a safe place {% hint style="warning" %} You may only view your API key on creation, so please be sure to copy the key as it will no longer be visible to you once you exit the page. If you lose your key, you may log into your account portal to manage your existing keys and generate new ones. {% endhint %}
Now, proceed with the below steps. {% tabs %} {% tab title="JavaScript" %} ```javascript npm install form-data ``` {% endtab %} {% tab title="Python" %} ```python pip install requests ``` {% endtab %} {% endtabs %} {% tabs %} {% tab title="JavaScript" %} ```javascript export TOPAZ_API_KEY="PASTE_YOUR_API_KEY_HERE" ``` {% endtab %} {% tab title="Python" %} ```python export TOPAZ_API_KEY="PASTE_YOUR_API_KEY_HERE" ``` {% endtab %} {% endtabs %} Now you can call our [Enhance endpoint](broken://spaces/z77V5aSS5QsChodPQbj5/pages/8d7df663a707a6b5d8ab65c5b5fe41edd74cf241) using the Topaz Labs client: {% tabs %} {% tab title="JavaScript" %} ```javascript import fs from 'fs'; import FormData from 'form-data'; const API_KEY = process.env.TOPAZ_API_KEY; const HEADERS = { 'X-API-KEY': API_KEY }; const IMAGE_BASE = 'https://api.topazlabs.com/image/v1'; // Submit the job const form = new FormData(); form.append('model', 'Standard V2'); form.append('output_format', 'jpeg'); form.append('image', fs.createReadStream('photo.jpg')); const response = await fetch(`${IMAGE_BASE}/enhance/async`, { method: 'POST', headers: { ...HEADERS, ...form.getHeaders() }, body: form, }); const { process_id } = await response.json(); // Poll for completion let status; do { await new Promise(resolve => setTimeout(resolve, 2000)); const statusRes = await fetch(`${IMAGE_BASE}/status/${process_id}`, { headers: HEADERS, }); ({ status } = await statusRes.json()); console.log(`Status: ${status}`); if (status === 'Failed' || status === 'Cancelled') { throw new Error(`Job ended with status: ${status}`); } } while (status !== 'Completed'); // Download the result const downloadRes = await fetch(`${IMAGE_BASE}/download/${process_id}`, { headers: HEADERS, }); const { url } = await downloadRes.json(); console.log(`Download your image: ${url}`); ``` {% endtab %} {% tab title="Python" %} ```python import os import time import requests API_KEY = os.environ["TOPAZ_API_KEY"] HEADERS = {"X-API-KEY": API_KEY} IMAGE_BASE = "https://api.topazlabs.com/image/v1" # Submit the job response = requests.post( f"{IMAGE_BASE}/enhance/async", headers=HEADERS, data={ "model": "Standard V2", "output_format": "jpeg" }, files={"image": open("photo.jpg", "rb")} ) process_id = response.json()["process_id"] # Poll for completion while True: status = requests.get( f"{IMAGE_BASE}/status/{process_id}", headers=HEADERS ).json()["status"] print(f"Status: {status}") if status == "Completed": break elif status in ("Failed", "Cancelled"): raise Exception(f"Job ended with status: {status}") time.sleep(2) # Download the result download_url = requests.get( f"{IMAGE_BASE}/download/{process_id}", headers=HEADERS ).json()["url"] print(f"Download your image: {download_url}") ``` {% endtab %} {% endtabs %} We have now made more popular image models such as Wonder 2, Bloom Creative, and Recover 3 more available as ready-to-use APIs so that you can easily integrate them into your applications.
Cover image
Wonder 2
Generative Image Upscaling		/pages/HViiwPD2MYLsh3kLA7kO
Bloom Creative
Creative Image Upscaling		/files/q2n3NmocgIsHgsKHeLzN/pages/PzZoYOpwL5VbtlsRYdJU
Once you find a model that you want to use in our "Models" tab, you can grab the URL from the model's dedicated page. Individual model pages also provide some important information about the model including use cases and examples of how you can call it. Check out our [API Playground](https://playground.topazlabs.com/) to tinker with these models and let us know your feedback and questions on our [Discord](https://discord.gg/vBCCwr28ZH).
How do I make an API call from the API Playground?
It's now easier more than ever to create and send your first API request. Once you have a Topaz Labs account and you have created your first API key, navigate over to our [API Playground](https://playground.topazlabs.com/) to better understand how to build requests. Please see the walkthrough above for an example of an image being upscaled with our Enhance Synchronous endpoint on the Image API.
### More Information
API Restrictions * The API has access rate limits depending on the current load on the servers. If you receive a HTTP 429 response, please try again (soon). We recommend using an exponential backoff for the requests to avoid immediately hitting the limit again. * The API only responds to HTTPS-secured communications. Any requests sent via HTTP return an HTTP 301 redirect to the corresponding HTTPS resources. * The API enforces a request size limit of 500MB. If a request exceeds this limit, the server responds with an HTTP 413. Please ensure that requests stay within the size constraint to avoid this error.
Please reach out to with any questions. # Video API Quickstart In this example, we’ll be using one of our popular video models, Apollo. Before we proceed, you need to create an [API key](https://account.topazlabs.com/manage-api). This key will be used to authenticate your requests to the Topaz Labs API.
How do I get my API key? In order to get access to the API, you'll need to [log into](http://topazlabs.com/account) your Topaz Labs account and create your unique API key. If you don't have an account, please follow the link [here](https://topazlabs.com/wp-login.php?action=register) to register.
1. Log into your Topaz Labs account from our [website](https://topazlabs.com/my-account/) 2. Navigate to the **API Keys** section in your account portal, enter a name, and click **Create** 3. Copy your API key (displayed at the top of the screen) and store it in a safe place {% hint style="warning" %} You may only view your API key on creation, so please be sure to copy the key as it will no longer be visible to you once you exit the page. If you lose your key, you may log into your account portal to manage your existing keys and generate new ones. {% endhint %}
Now, proceed with the below steps. {% stepper %} {% step %} ### Create Video Request Create a video requestβ€”just include some details about the source video, output parameters, and desired enhancements. {% hint style="info" %} Visit out [API Reference](https://developer.topazlabs.com/api-reference) page for up-to-date functionality. This endpoint is free to use. {% endhint %} ```c curl --request POST \ --url https://api.topazlabs.com/video/ \ --header 'X-API-Key: Your-API-Key' \ --header 'accept: application/json' \ --header 'content-type: application/json' \ --data ' { "source": { "resolution": { "width": 800, "height": 448 }, "container": "mp4", "size": 477010, "duration": 4, "frameRate": 24, "frameCount": 97 }, "output": { "resolution": { "width": 800, "height": 448 }, "audioCodec": "AAC", "audioTransfer": "Copy", "frameRate": 24, "dynamicCompressionLevel": "High", "container": "mp4" }, "filters": [ { "model": "apo-8", "slowmo": 1, "fps": 60, "duplicate": true, "duplicateThreshold": 0.1 } ] }' ``` {% endstep %} {% step %} ### Accept & Upload Video Request After submitting the video request, you can choose to continue by calling this endpoint. ```c curl --request PATCH \ --url https://api.topazlabs.com/video/[your-requestID]/accept \ --header 'X-API-Key: Your-API-Key' \ --header 'accept: application/json' ``` Once this endpoint is called, you will receive a set of URL(s). You may use the following code snippet to upload the video to that link from your local device. {% hint style="info" %} In this example, we will upload the entire video file to a single URL due to its small file size. {% endhint %} ```c S3_UPLOAD_URL=[https://...] curl --verbose --request PUT \ --upload-file "Your-Video-File" \ --header "Content-Type: video/mp4" \ "$S3_UPLOAD_URL" ``` Once uploaded, you'll receive some information about your upload, including your *eTag* number. This will be useful for the next step. {% endstep %} {% step %} ### Complete Video Upload After you have finished uploading your video segments, you may use the following request to confirm that all of your video segments have been received. Once this endpoint is called, you video will begin processing with its enhancements. ```c curl --request PATCH \ --url https://api.topazlabs.com/video/[your-requestID]/complete-upload \ --header 'X-API-Key: Your-API-Key' \ --header 'accept: application/json' \ --header 'content-type: application/json' \ --data '{ "uploadResults": [ { "partNum": 1, "eTag": "your-eTag" } ] }' ``` You should receive a response confirming that your request is queued for processing once you have called the endpoint. {% endstep %} {% step %} ### Get Video Status You may use the following request to view the status of your video request ```c curl --request GET \ --url https://api.topazlabs.com/video/[your-requestID]/status \ --header 'X-API-Key: Your-API-Key' \ --header 'accept: application/json' ``` Once your video has finished processing, you will receive a link to download your video as a response to this endpoint. {% endstep %} {% endstepper %} Congratulations! You have just completed your first Video API request! πŸŽ‰ We have now made popular video models such as Proteus, Starlight Precise, and Astra Creative more available as ready-to-use APIs so that you can easily integrate them into your applications.
Cover image
Proteus
Precision Video Upscaling		/files/MGibasuJtWp1C6I2erc1/pages/S3PS8lsDXyUoyG7azmer
Starlight Precise 2
Generative Video Upscaling		/files/HvwdNoTx8LEISVgc2p8q/pages/aL31hOSUmaDJyjy6MMLU
Once you find a model that you want to use in our "Models" tab, you can grab the URL from the model's dedicated page. Individual model pages also provide some important information about the model including use cases and examples of how you can call it. Check out our [API Playground](https://playground.topazlabs.com/) to tinker with these models and let us know your feedback and questions on our [Discord](https://discord.gg/vBCCwr28ZH).
How do I make an API call from the API Playground?
It's now easier more than ever to create and send your first API request. Once you have a Topaz Labs account and you have created your first API key, navigate over to our [API Playground](https://playground.topazlabs.com/) to better understand how to build requests. Please see the walkthrough above for an example of an image being upscaled with our Enhance Synchronous endpoint on the Image API.
### More Information
API Restrictions * The API has access rate limits depending on the current load on the servers. If you receive a HTTP 429 response, please try again (soon). We recommend using an exponential backoff for the requests to avoid immediately hitting the limit again. * The API only responds to HTTPS-secured communications. Any requests sent via HTTP return an HTTP 301 redirect to the corresponding HTTPS resources. * The API enforces a request size limit of 500MB. If a request exceeds this limit, the server responds with an HTTP 413. Please ensure that requests stay within the size constraint to avoid this error.
Please reach out to with any questions. # Model Selection We recommend starting with what you are trying to do, then selecting the best model from there. ### Image
Upscale an Image Three tiers, each with a different tradeoff: | | Gigapixel | Wonder | Bloom | | --------------- | ---------------------------------------------------- | -------------------------------------------------------------------------- | ----------------------------------------------------- | | **Tier** | Precision | Generative | Creative | | **Description** | Precision Image Upscale & Enhancement | Generative Image Upscale & Enhancement | Creative Image Upscale & Enhancement | | **Intent** | Improve resolution, preserve source characteristics. | Improve and restore by adding detail and texture, while preserving intent. | Transform with new, creative detail or stylization. | | **Use Case** | General purpose upscaling & enhancement. | Upcaling, restoring and improving low resolution or compressed sources. | Upscaling, improving, and transforming GenAI sources. | #### Gigapixel | Model | Use Case | | -------------------------------------------------------------------------------- | ------------------------------------------------ | | [`Standard 2`](/image-models/gigapixel/standard-2) | Default β€” works for most images | | [`High Fidelity 2`](/image-models/gigapixel/high-fidelity-2) | Maximum source preservation | | [`Low Resolution 2`](/image-models/gigapixel/low-resolution-2) | Very small inputs (thumbnails, web scrapes) | | [`Art & CGI`](/image-models/gigapixel/art-and-cgi) | Illustrations, renders, game assets, digital art | | [`Text & Shapes`](/image-models/gigapixel/text-and-shapes) | Documents, screenshots, text-heavy images | | [`Recover Faces`](/image-models/gigapixel/recover-faces) | Portraits where facial detail is the priority | | [`Transparent Image Upscale`](/image-models/gigapixel/transparent-image-upscale) | PNGs with alpha channels | #### Wonder | Model | Use Case | | ------------------------------------------------------ | ------------------------------------------------- | | [`Standard Max`](/image-models/wonder/standard-max) | Default generative upscaling | | [`Wonder 2`](/image-models/wonder/wonder-2) | Stronger generation for more detail | | [`Redefine: Realistic`](/image-models/wonder/redefine) | Generative enhancement grounded in photorealism | | [`Redefine: Creative`](/image-models/wonder/redefine) | Generative enhancement with more creative freedom | | [`Recover 3`](/image-models/wonder/recover-3) | Heavily degraded or damaged sources | #### Bloom | Model | Use case | | -------------------------------------------------------- | -------------------------- | | [`Bloom Creative`](/image-models/bloom/bloom-1-creative) | Maximum stylization | | [`Bloom Realism`](/image-models/bloom/bloom-1-realism) | Creative but more grounded |
Sharpen or Deblur **Standard** β€” use when you know the blur type: | Model | Use case | | ------------------------------------------------------------------------------ | ----------------------------------------------- | | [`Sharpen`](/image-models/removal-and-cleanup/sharpen/standard) | General-purpose β€” good starting point | | [`Sharpen Strong`](/image-models/removal-and-cleanup/sharpen/strong) | Noticeably soft images | | [`Sharpen Natural`](/image-models/removal-and-cleanup/sharpen/natural) | Subtle sharpening that avoids over-processing | | [`Sharpen Lens Blur 2`](/image-models/removal-and-cleanup/sharpen/lens-blur-2) | Optical blur from lens softness or missed focus | | [`Sharpen Motion Blur`](/image-models/removal-and-cleanup/sharpen/motion-blur) | Blur from camera or subject movement | | [`Sharpen Refocus`](/image-models/removal-and-cleanup/sharpen/refocus) | Slightly out-of-focus images | | [`Portrait`](/image-models/removal-and-cleanup/sharpen/portrait) | Optimized for faces and skin texture | | [`Wildlife`](/image-models/removal-and-cleanup/sharpen/wildlife) | Optimized for fur, feathers, scales | **Generative** β€” use when the source is heavily degraded or you're unsure of the blur type: | Model | Use case | | -------------------------------------------------------------------------- | -------------------------------------------------------------- | | [`Super Focus 2`](/image-models/removal-and-cleanup/sharpen/super-focus-2) | Generative sharpening that recovers detail beyond the original |
Reduce Noise or Grain Pick based on noise severity: | Model | Use case | | -------------------------------------------------------------------------- | ----------------------------------------------------- | | [`Denoise Normal`](/image-models/denoise/normal) | Light noise β€” well-lit conditions | | [`Denoise Strong`](/image-models/denoise/strong) | Moderate noise β€” high ISO, low light | | [`Denoise Extreme`](/image-models/denoise/extreme) | Heavy noise β€” very high ISO, underexposed | | [`Dust & Scratch 2`](/image-models/removal-and-cleanup/dust-and-scratch-2) | Film scans or archival images with physical artifacts |
Remove Objects or Backgrounds | Model | Use case | | -------------------------------------------------------------------------------- | ------------------------------------------------- | | [`Background Removal`](/image-models/removal-and-cleanup/background-removal) | Remove the background entirely | | [`Image Object Matting`](/image-models/removal-and-cleanup/image-object-matting) | Extract subject with transparency for compositing |
Correct Color or Lighting | Model | Use case | | --------------------------------------------------------------------------- | --------------------------------------- | | [`Balance Color`](/image-models/color-and-lighting/balance-color) | Auto white balance and color correction | | [`Adjust Lighting 2`](/image-models/color-and-lighting/adjust-lighting-2) | Exposure and contrast adjustment | | [`Image Colorization`](/image-models/color-and-lighting/image-colorization) | Convert black-and-white to color |
### Video
Upscale or Enhance a Video Three families, each with a different tradeoff: | | Proteus | Starlight | Astra | | --------------- | ---------------------------------------------------- | -------------------------------------------------------------------------- | ----------------------------------------------------- | | **Tier** | Precision | Generative | Creative | | **Description** | Precision Video Upscale & Enhancement | Generative Video Upscale & Enhancement | Creative Video Upscale & Enhancement | | **Intent** | Improve resolution, preserve source characteristics. | Improve and restore by adding detail and texture, while preserving intent. | Transform with new, creative detail or stylization. | | **Use Case** | General purpose upscaling & enhancement. | Upcaling, restoring and improving archival and GenAI | Upscaling, improving, and transforming GenAI sources. | #### Proteus **Don't know where to start?** Use **Proteus**. Then narrow down if your source has specific characteristics: | Model | Use case | | -------------------------------------------------------------------- | -------------------------------------------------------------------- | | [`Proteus`](/video-models/proteus/proteus) | Default β€” handles most content well | | [`Proteus Natural`](/video-models/proteus/proteus-natural) | Lighter processing, stays closest to the original | | [`Artemis HQ / MQ / LQ`](/video-models/proteus/artemis) | Match to your source quality β€” HQ for clean footage, LQ for degraded | | [`Artemis Aliasing/Moire`](/video-models/proteus/artemis) | Visible aliasing or moire patterns | | [`Artemis Medium Halo / Strong Halo`](/video-models/proteus/artemis) | Halo artifacts from older upscaling or edge enhancement | | [`Dione TV / DV`](/video-models/proteus/dione) | Interlaced broadcast (TV) or camcorder (DV) footage | | [`Dione Robust`](/video-models/proteus/dione) | Interlaced content with heavy degradation | | [`Dione Dehalo / Robust Dehalo`](/video-models/proteus/dione) | Interlaced content with halo artifacts | | [`Gaia 2 (Animation)`](/video-models/proteus/gaia) | Animation and single-frame animation | | [`Gaia HQ / CG`](/video-models/proteus/gaia) | High-quality or general CG and rendered content | | [`Iris MQ / LQ`](/video-models/proteus/iris) | Legacy content at medium or low quality | | [`Rhea`](/video-models/proteus/rhea) | General enhancement with natural texture | | [`Theia Fine Tune Detail`](/video-models/proteus/theia) | Push detail enhancement β€” more aggressive | | [`Theia Fine Tune Fidelity`](/video-models/proteus/theia) | Preserve original look β€” lighter touch | #### Starlight Quality and Fast subtiers. Use Quality when output matters most, Fast when speed or cost is the priority. | Model | Subtier | Use case | | ------------------------------------------------------------------------------- | ------- | ------------------------------------------ | | [`Starlight HQ`](/video-models/starlight/starlight-hq) | Quality | Maximum quality generative output | | [`Starlight Precise 2`](/video-models/starlight/starlight-precise-2-deprecated) | Quality | Default for most generative work | | [`Starlight Precise 1`](/video-models/starlight/starlight-precise-1-deprecated) | Quality | Highest fidelity to source | | [`Starlight Sharp`](/video-models/starlight/starlight-sharp) | Quality | Emphasis on sharpness and edge detail | | [`Starlight Fast 2`](/video-models/starlight/starlight-fast-2) | Fast | Best fast model β€” start here for speed | | [`Starlight Fast 1`](/video-models/starlight/starlight-fast-1-deprecated) | Fast | Speed-optimized generative enhancement | | [`Starlight Mini`](/video-models/starlight/starlight-mini) | Fast | Lightest β€” previews or cost-sensitive jobs | #### Astra | Model | Use case | | --------------------------------------------------- | ----------------------------- | | [`Astra 1`](/video-models/astra/astra-1-deprecated) | Creative video transformation |
Reduce Noise or Grain #### Denoise Quality and Fast subtiers via the Nyx family: | Model | Subtier | Use case | | -------------------------------------------------------------- | ------- | ---------------------------------------------- | | [`Nyx`](/video-models/denoise/nyx) | Quality | Default β€” balanced noise reduction and detail | | [`Nyx XL`](/video-models/denoise/nyx-xl) | Quality | Stronger reduction for heavy noise | | [`Nyx High Fidelity`](/video-models/denoise/nyx-high-fidelity) | Quality | Maximum detail preservation, lighter reduction | | [`Nyx Fast`](/video-models/denoise/nyx-fast) | Fast | Speed-optimized denoising |
Change Frame Rate or Create Slow-Mo #### Frame Interpolation Quality and Fast subtiers. Generates new frames to increase frame rate or create slow motion. | Model | Subtier | Use case | | ------------------------------------------------------ | ------- | ------------------------------------------------------- | | [`Apollo`](/video-models/frame-interpolation/apollo) | Quality | Default β€” best all-around quality | | [`Chronos`](/video-models/frame-interpolation/chronos) | Quality | Alternative algorithm for fast action or complex scenes | | [`Aion`](/video-models/frame-interpolation/aion) | Quality | Additional option for specific content types | | [`Apollo Fast`](broken://pages/dNHtFXtpCMkrraa22s9w) | Fast | Speed-optimized | | [`Chronos Fast`](broken://pages/5rUaTuF8aMBBuSfjWfg0) | Fast | Speed-optimized alternative algorithm |
Deblur or Colorize #### Video Utilities | Model | Use case | | ------------------------------------------------------------------------ | ----------------------------------------------------- | | [`Themis 2`](/video-models/video-utilities/themis-2-motion-deblur) | Remove motion blur from camera shake or fast movement | | [`Video Colorization`](/video-models/video-utilities/video-colorization) | Convert B\&W or desaturated footage to color |
# API Key Setup In order to get access to the API, you'll need to [log into](http://topazlabs.com/account) your Topaz Labs account and create your unique API key. If you don't have an account, please follow the link [here](https://topazlabs.com/wp-login.php?action=register) to register.
1. Log into your Topaz Labs account from our [website](https://topazlabs.com/my-account/) 2. Navigate to the **API Keys** section in your account portal, enter a name, and click **Create** 3. Copy your API key (displayed at the top of the screen) and store it in a safe place {% hint style="warning" %} You may only view your API key on creation, so please be sure to copy the key as it will no longer be visible to you once you exit the page. If you lose your key, you may log into your account portal to manage your existing keys and generate new ones. {% endhint %} # Tier Pricing Flexible, per-use pricing that scales with you Pay only for what you process β€” billed per output megapixel across all image models. No subscriptions, no minimums, no expiration. Use our [credit calculator](https://www.claudeusercontent.com/?domain=claude.ai\&errorReportingMode=parent\&formattedSpreadsheets=true#) to estimate costs before you build. ### Credits Credits are the currency of the Topaz Labs API. All image processing is billed in credits, deducted automatically when a job completes. ### How MP Output is Calculated Billing is based on the **output** resolution of your processed image β€” not the input. ### Model Family Pricing All models are available on a pay-per-use basis. The following are the pricing families for our Image API and Video API. #### Image Pricing {% hint style="info" %} Image models are priced linearly based on MP output (e.g. 1 credit = 24 MP of output). {% endhint %} | Use Case | Model Family | Output MP Per Credit | | ------------------ | -------------------------------------------------------- | ---------------------------------- | | Precision Upscale | [`Gigapixel`](/image-models/gigapixel) | 24 | | Generative Upscale | [`Wonder`](/image-models/wonder) | 4 | | Creative Upscale | [`Bloom`](/image-models/bloom) | 2 | | Sharpen | [`Sharpen`](/image-models/removal-and-cleanup/sharpen) |

GAN β€” 24
Generative β€” 20

| | Denoise | [`Denoise`](/image-models/denoise) | 24 | | Image Utilities | [`Removal & Cleanup`](/image-models/removal-and-cleanup) | 24 | | Image Utilities | [`Color & Lighting`](/image-models/color-and-lighting) | 24 | #### Video Pricing {% hint style="info" %} Video credit costs are all estimates calculated based on 10s at 1080p 30fps. For pricing tables at various durations and output resolutions, visit the model family pages linked below. We recommend using out our [credit calculator](https://developer.topazlabs.com/credit-calculator) for larger batch estimates. {% endhint %} | Use Case | Model Family | Credits Per Video | | ------------------ | ---------------------------------------------------------- | ------------------------------- | | Precision Upscale | [`Proteus`](/video-models/proteus) | 4 | | Generative Upscale | [`Starlight`](/video-models/starlight) |

Fast β€” 6
Quality β€” 12

| | Creative Upscale | [`Astra`](/video-models/astra) | 40 | | Denoise | [`Denoise`](/video-models/denoise) |

Fast β€” 2
Quality β€” 4

| | Motion | [`Frame Interpolation`](/video-models/frame-interpolation) |

Fast β€” 1
Quality β€” 2

| | Video Utilities | [`Video Utilities`](/video-models/video-utilities) | 2 | {% hint style="info" %} There are a few exceptions to some of the families. Click into a given family to view all prices, or view our individual model pricing page. {% endhint %} To access our most update-to-date pricing, please visit our [website](https://www.topazlabs.com/enhance-api). Looking for a custom solution? Contact our team at and we'll be in touch about our enterprise plans. # Individual Model Pricing | Model | Type | Price | | ------------------------- | ----- | ---------------------------------- | | Standard 2 | Image | 24 | | High Fidelity 2 | Image | 4 | | High Fidelity 3 | Image | 2 | | Low Resolution 2 | Image |

GAN β€” 24
Generative β€” 20

| | Art & CGI | Image | 24 | | Transparent Image Upscale | Image | 24 | | Detail Faces | Image | 24 | | Recover Faces | Image | | | Face Recovery 3 | Image | | | Text & Shapes | Image | | | Redefine | Image | | | Wonder | Image | | | Wonder 2 | Image | | | Wonder 3 | Image | | | Standard Max | Image | | | Recover 3 | Image | | | Bloom Creative | Image | | | Bloom Realism | Image | | | Denoise Normal | Image | | | Denoise Strong | Image | | | Denoise Extreme | Image | | | Denoise Max | Image | | | Dust & Scratch 2 | Image | | | Image Object Matting | Image | | | Background Removal | Image | | | Sharpen Standard | Image | | | Sharpen Strong | Image | | | Noise-Aware Sharpen | Image | | | Portrait | Image | | | Wildlife | Image | | | Natural | Image | | | Refocus | Image | | | Motion Blur | Image | | | Lens Blur 2 | Image | | | Super Focus 2 | Image | | | Super Focus 3 | Image | | | Adjust Lighting 2 | Image | | | Balance Color | Image | | | Image Colorization | Image | | | Proteus | Video | | | Proteus Natural | Video | | | Rhea | Video | | | Theia | Video | | | Theia Fine Tune Detail | Video | | | Theia Fine Tune Fidelity | Video | | | Artemis Aliasing / Moire | Video | | | Artemis Low Quality | Video | | | Artemis Medium Quality | Video | | | Artemis High Quality | Video | | | Artemis Medium Halo | Video | | | Artemis Strong Halo | Video | | | Dione DV | Video | | | Dione TV | Video | | | Dione Robust | Video | | | Dione Dehalo | Video | | | Dione Robust Dehalo | Video | | | Gaia High Quality | Video | | | Gaia CG | Video | | | Gaia 2 (Animation) | Video | | | Iris Low Quality | Video | | | Iris Medium Quality | Video | | | Starlight Precise 2.5 | Video | | | Starlight HQ | Video | | | Starlight Mini | Video | | | Starlight Sharp | Video | | | Starlight Fast 2 | Video | | | Astra 1 | Video | | | Astra 2 | | | | Nyx | | | | Nyx High Fidelity | | | | Nyx XL | | | | Nyx Fast | | | | Aion | | | | Apollo | | | | Apollo Fast | | | | Chronos | | | | Chronos Fast | | | | Themis 2 (Motion Deblur) | | | | Video Colorization | | | | Hyperion (SDR to HDR) | | | | Hyperion 2 (SDR to HDR) | | | | | | | # API Limits # Gigapixel Precision Upscaling for Images ### Model Family Overview Essential image enhancement models designed for quality, precision, and control. {% hint style="info" %} Precision models attempt to improve quality without changing the source characteristics. {% endhint %} ### Key Features * Industry-standard upscaling for photo, graphics, and print * Advanced face recovery with generative and non-generative options: restore detail and faces in previously unrecoverable images. * Precise, true-to-input image enhancement. ### Pricing This family is priced at 1 credit per 24 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1111122335
### Models
Cover image
Standard 2/files/CDhWgEFO3WZBsmoWKxpJ/pages/AR5gcpGM5m2L7RxdD8Pl
High Fidelity 2/files/8eDQygn11PiEWDQOtePx/pages/do1KZmQYfzVi62S999Ym
Low Resolution 2/files/Wchvu3jjzqUJjRYsAlhJ/pages/hGlCSws5dGfV38YgDnQm
Art & CGI/files/o5hMGBUfcmj7C272tsAZ/pages/xjZ3pTByAOKMjeKoZIMM
Transparent Image Upscale/files/xSkSFhSmBrAuuO0mDa1S/pages/dqnh7OYcRAvI9CJ6fy8t
Detail Faces/files/vlM9AcwIyWzsQwQLKmxd/pages/FdWPgRt3fwaKh1YhjfHG
Recover Faces/files/xSEgdUIA78xPr8sW3P8J/pages/qjTe0ReznYIkoakYH1Vh
Text & Shapes/files/CkJc80Nzm2fBaY9Qx5Q6/pages/V0KDIPlaS5KxhqJUPL0y
# Standard 2 General-purpose model balancing detail, sharpness, and noise reduction ### Model Overview **Standard 2** is the general-purpose image upscaling model recommended for most photos and graphics. It delivers clean, reliable enlargement across a wide range of image types while maintaining true-to-input detail and structure. ### Key Capabilities * Trusted, industry-standard image upscaling * Preserves natural detail and texture * Balanced model is Ideal default choice for photos, graphics, and print ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Standard V2"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 1024 MP ### Examples
Cover image
Click to view/files/5L9txJiMtqbGYfB6WJYuhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FBird.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FBird%20Standard%202%204x.png&src2label=After&zoom=1
# High Fidelity 2 Fidelity upscaling for high-resolution images and professional photos ### Model Overview **High Fidelity 2** is a precision upscaling model designed for images that are already high resolution and well captured. It focuses on enlarging images while preserving fine detail, natural texture, and structural accuracy, avoiding aggressive reconstruction or over-sharpening. ### Key Capabilities * High-fidelity upscaling for already high-resolution sources * Preserves fine detail and original texture during enlargement ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"High Fidelity V2"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters ### Examples
Cover image
Click to view/files/S5joUmZcvXFgrNVQN8oShttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FHigh%20Fidelity%20Before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FHigh%20Fidelity%20v2%2002.jpg&src2label=After&zoom=1
Click to view/files/JXSrhqcPc1r3UAJdtIzXhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-pixabay-70080.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FHigh%20Fid%204xpexels-pixabay-70080-gigapixel-high%20fidelity%20v2-4x.jpg&src2label=After&zoom=1
# High Fidelity 3 Improved fidelity upscaling for high-resolution images and professional photos ### Model Overview **High Fidelity 3** is a precision upscaling model designed to deliver the best results on high-resolution sources. This model improves on High Fidelity 2 with enhanced resolution scaling and minimal detail loss or artifacting. It focuses on preserving original image structure and realism, reducing the plasticky appearance and excess artifacts seen in earlier models while maintaining a clean, natural output. High Fidelity 3 performs best on medium to high and high quality images, including modern photos, RAW images, and smartphone photography, and supports a wide range of content such as portraits, landscapes, wildlife, and images with graphics. ### Key Capabilities * Higher quality upscaling with improved detail retention and fewer artifacts compared to High Fidelity 2. * Preserves natural image structure with reduced plasticky appearance and more consistent textures. * Optimized for high-quality images, delivering clean results beyond traditional resizing. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Upscale High Fidelity V3"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `recovery_strength` β€” float from 0.0 to 1.0, default 1.0 * `opacity` β€” float from 0.0 to 1.0, default 1.0 ### Examples
Cover image
Click to view/files/zVwiIEB2chiTXnyCv09qhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/model-examples/harvey_before.webp&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/harvey_after.png&src2label=After&zoom=1
Click to view/files/kRjzMNvCY5nka1jlV0pRhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/model-examples/coffee_shop_before.jpg&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/coffee_shop_after.png&src2label=After&zoom=1
# Low Resolution 2 Recovery-focused upscaling for low resolution or heavily compressed sources ### Model Overview **Low Resolution 2** is optimized for images that start with limited detail, heavy compression, or small dimensions. It focuses on intelligent reconstruction to recover usable detail from challenging sources without modifying the source characteristics. ### Key Capabilities * Designed for low-resolution and compressed images * Recovers usable detail from difficult inputs * Improves clarity while avoiding exaggerated artifacts ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Low Resolution V2"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 1024 MP ### Examples
Cover image
Click to view/files/XQosiSrfdwsdKHw2NqN4https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-ivars-773583%201.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGrass%20Field%20Low%20Res%204xpexels-ivars-773583%201-gigapixel-low%20resolution%20v2-4x.png&src2label=After&zoom=1
# Art & CGI Precision upscaling for artwork, drawings, illustrations, and computer graphics ### Model Overview **Art & CGI** is tailored for non-photographic imagery such as illustrations, digital art, renders, and stylized graphics. It preserves clean edges, flat color regions, and intentional line work without introducing photographic texture. ### Key Capabilities * Optimized for illustrations, digital art, and CGI * Preserves clean edges and flat color areas * Avoids unwanted photographic texture or noise ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"CGI"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `deblur_strength` β€” decimal between 0 and 1, default 0.5 * Adjusts the strength of the deblur. **Resolution Limits** * `input` β€” 512 MP * `output` β€” 1024 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F948688_9486882.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FArt948688_9486882-gigapixel-cgi-4x.jpg&src2label=After&zoom=1/files/sf139yvMv6wKy0SSpx3m
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-steve-28918449.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FArtpexels-steve-28918449-gigapixel-cgi-4x.jpg&src2label=After&zoom=1/files/zBEfuCyhQAUaWTqVdMm4
# Transparent Image Upscale Preserve Alpha Transparency ### Model Overview A specialized upscaling model designed specifically for images with transparency, including logos, icons, titles, and graphic overlays. This model enhances resolution while preserving alpha channel integrity, ensuring that edges, cutouts, and semi-transparent regions remain clean and artifact-free without affecting the background. ### Key Capabilities * Preserves alpha channels and transparency with pixel-accurate edge handling * Ideal for logos, lower thirds, UI elements, and composited graphics requiring clean edges ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Transparency Upscale"` **Model-Specific Parameters** * No parameters ### Examples
Cover image
Click to view/files/k01apEjvwmhvbABrE74Rhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F78c798f8-9440-42e9-90e0-8f997dfc806f.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FTransparent%20Upscale%204x.png&src2label=After&zoom=1
# Detail Faces Improve realism in AI-generated faces ### Model Overview **Detail Faces** is a specialized enhancement model designed to improve facial detail and realism in AI-generated images. It restores natural texture in skin, eyes, and hair while reducing artificial smoothness, producing sharper, more lifelike results without compromising the subject’s identity. ### Key Capabilities * Enhances facial features with natural detail in skin, hair, and eyes. * Reduces β€œplastic” or uncanny valley artifacts for more realistic, lifelike results. * Improves clarity in clothing and fine textures for overall image fidelity. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Detail"` **Model-Specific Parameters** * `detail_strength` β€” decimal between 0 and 10, default 6.0 {% hint style="info" %} This model works best on large images, where the *face* in the input image is at least is 512 x 512 pixels. For smaller images, we recommend using [`Recover Faces`](/image-models/gigapixel/recover-faces) {% endhint %} ### Examples
Cover image
Click to view/files/xH76t07eN5z8Cx5FgELchttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-alexandrecanteiro-33406874%201.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fdf0dac7c-b1b4-45af-b821-2d7f1025df54.png&src2label=After&zoom=1
# Recover Faces Intelligent facial Restoration for low-resolution images ### Model Overview **Recover Faces** is a specialized facial reconstruction model designed to restore recognizable facial detail from low-resolution, damaged, or heavily compressed images. When facial information is missing or unreadable, Recover Faces reconstructs plausible features rather than strictly preserving original pixels. This model is typically combined with another enhancement. Face Recovery includes both Realistic and Creative variants, allowing users to balance fidelity and recovery strength based on source quality. Because these models are reconstructive by design, results may include subtle changes to expressions or smoothing of skin, hair, or fine facial details in order to produce a coherent, usable face. Recover Faces is intended for portraits and people-focused imagery where standard upscaling cannot recover meaningful facial structure. ### Key Capabilities * Reconstructs facial detail from extremely low-resolution or damaged images * Automatically detects and processes multiple faces within a single image * Enables usable portrait results where traditional upscaling fails ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Faces"` **Model-Specific Parameters** * `strength` β€” decimal between 0 and 1, default 0.8 * `noise_sigma` β€” decimal between 0.001 and 0.1, default 0.015 * `blur_sigma` β€” decimal between 0.01 and 2.0, default 0.4 * `noise_seed` β€” integer between 1 and 2000, default 1 * `reference_uri` β€” string, optional {% hint style="info" %} This model works best on smaller images, where the *face* in the input image is less than 512 x 512 pixels. For larger images, we recommend using [`Detail Faces`](/image-models/gigapixel/detail-faces). {% endhint %} ### Examples
Cover image
Click to view/files/tXrX8PeOGS625oD640Puhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FCrowd%201.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRecover%20Crowd%204xCrowd%201.png&src2label=After&zoom=1
# Face Recovery 3 Improved face restoration for low-resolution images ### Model Overview **Face Recovery 3** is an updated facial reconstruction model designed to restore recognizable facial detail from low-resolution, damaged, or heavily compressed images. When facial information is missing or unreadable, Face Recovery 3 reconstructs plausible features rather than strictly preserving original pixels. This model is typically combined with another enhancement model. Face Recovery 3 includes both Realistic and Creative variants, allowing users to balance fidelity and recovery strength based on source quality. The updated model produces more natural and realistic faces with improved skin, hair, and facial detail reconstruction while maintaining coherent, usable portrait results. Because these models are reconstructive by design, results may include subtle changes to expressions or fine facial characteristics. Face Recovery 3 is intended for portraits and people-focused imagery where standard upscaling cannot recover meaningful facial structure. ### Key Capabilities * Reconstructs facial detail from extremely low-resolution or damaged images. * Produces more realistic and natural-looking faces with improved facial detail recovery. * Automatically detects and processes multiple faces within a single image. * Enables usable portrait results where traditional upscaling fails. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Faces"` **Model-Specific Parameters** * `grain` β€” bool, optional, default `false` * Whether to add grain to the output * `grain_density` β€” decimal 010 to 1.0, optional, default 0.5 * Intensity of the grain effect (0.0 to 1.0) * `grain_model` β€” string, optional, default `'silver'` * Grain model: `'silver'`, `'gaussian'`, `'grey'` * `grain_size` β€” decimal 1.0 to 5.0, optional, default 1.0 * Size of the grain particles * `grain_strength` β€” decimal 0.0 to 1.0, optional, default 0.5 * Strength of the grain effect * `iai_packed_metadata` β€” array, optional, default `null` * Face bounding box and score metadata, as packed list or as a JSON-style string. * `input_height` β€” int, optional, default `null` * Input image height in pixels * `input_width` β€” int, optional, default `null` * Input image width in pixels * `output_height` β€” int, optional, default `null` * Output image height in pixels * `output_width` β€” int, optional, default `null` * Output image width in pixels * `reference_uri` β€” string, optional, default `null` * URI for reference image (faces used in face recovery) * `strength` β€” decimal from 0.0 to 1.0, default 1.0 * Denoise strength {% hint style="info" %} This model works best on smaller images, where the *face* in the input image is less than 512 x 512 pixels. For larger images, we recommend using [`Detail Faces`](/image-models/gigapixel/detail-faces). {% endhint %} ### Examples
Cover image
Click to view/files/nhH1IqpDvw0HSH1yLC9Uhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_before.jpeg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_after.png&src2label=After&zoom=1.0
Click to view/files/Ven3JWYHdEOOwRPbDX8Lhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_before.webp&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_after.png&src2label=After&zoom=1.0
# Text & Shapes Clean upscaling for graphics and typography ### Model Overview **Text & Shapes** is designed for images dominated by typography, logos, UI elements, and geometric shapes. It prioritizes edge clarity and shape accuracy during upscaling. ### Key Capabilities * Preserves sharp edges and geometric structure * Ideal for logos, UI, and graphic design assets * Maintains legibility during enlargement ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Text Refine"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `fix_compression` β€” decimal between 0 and 1 * Reduces compression artifacts to improve details. * `strength` β€” decimal between 0.01 and 1 * Controls model strength. Too high of a result can make results look unrealistic. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Adjusts the strength of the denoise. * `deblur_strength` β€” decimal between 0 and 1, default 0.5 * Adjusts the strength of the deblur. * `decompression_strength` β€” decimal between 0 and 1, default 0.5 * Adjusts the strength of the decompression. * `opacity` β€” decimal between 0 and 1, default 1.0 * Adjust strength of opacity. **Resolution Limits** * `input` β€” 512 MP * `output` β€” 1024 MP ### Examples
Cover image
Click to view/files/29bVKEMsMZpYX71odtlX
# Wonder Generative Upscaling for Images ### Model Family Overview Generative image enhancement models designed to recover and restore low quality images while retaining precise and natural details. {% hint style="info" %} Generative models attempt to improve image quality by adding recovered detail and texture while preserving the original image intent. {% endhint %} ### Key Features * Upscale, denoise and improve low resolution photos in 1 click. * Restore previously unrecoverable photos with high fidelity * Highest quality generative face recovery avoids plastic and synthetic looks ### Pricing This family is priced at 1 credit per 4 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits11246810131625
### Models
Cover image
Redefine/files/7sJ7IPFlxS4V5IXSvKVo/pages/ggujpXTpNtcWmsn0B4C9
Wonder/files/VaR4PK8s5skvK8nzKzHE/pages/cU4FcAXtsCCKxqR565L5
Wonder 2/files/eTCu0PWoCxs8JhbKjG3o/pages/HViiwPD2MYLsh3kLA7kO
Standard Max/files/bnCbiU6iqRJAyCEp5mb7/pages/rKzfAMkSjrHilil32pMv
Recover 3/files/jNV7Cbjkan6wpvoZaqRk/pages/YIWYZa6knxvIM9tKCO3P
# Redefine Generative diffusion model adds new detail with prompt-based enhancement ### Model Overview **Redefine** is a generative image enhancement model designed to add new detail and rebuild structure when original image information is missing or degraded. Unlike precision upscaling models, Redefine can generate photorealistic detail to restore clarity in blurry, low-resolution, or damaged images. Redefine is also the only local, prompt-driven generative image model available, giving artists direct control over generation without relying on cloud processing. Users can guide results using image prompts, creativity controls, and texture settings, making Redefine especially valuable for CGI, VFX, and creative workflows that require generative flexibility while working entirely on local hardware. ### Key Capabilities * Generative enhancement that adds new detail and structure; local and cloud * Prompt-driven control for creative and VFX workflows without cloud dependency * Powerful recovery of blurry, low-resolution, and heavily degraded images ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11246810131625
### Getting Started **Endpoint** * * `model` β€” `"Redefine"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 256 MP * `output` β€” 256 MP ### Examples
Cover image
Click to view
Redefine Realistic		/files/HrJZNl5Ov3hs0gzvTZq7https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRedefine%20Realistic%20Before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRedefine%20Realistic%20set%202%2002.jpg&src2label=After&zoom=1
Click to view
Redefine Creative		/files/SnEpP0Vozpicx8FQZFNehttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRedefine%20Realistic%20Before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRefine%20Creative%20.jpg&src2label=After&zoom=1
# Wonder A generative AI model designed for one-click repair and enhancement of low-to-medium resolution images ### Model Overview **Wonder** is a generative image enhancement model designed to repair and improve small to medium-sized low-resolution images in a single step. It intelligently reconstructs missing detail while prioritizing realism and avoiding unnecessary changes to objects, textures, or overall image structure. Wonder excels at restoring soft, noisy, or compressed images, producing clean, realistic results with minimal artifacts. It is best used when images require strong cleanup and realism-focused enhancement rather than fine-grained manual control. ### Key Capabilities * One-click generative enhancement for low- and medium-quality images * Delivers clean, realistic results without artifact buildup * Designed for single-step image repair when realism matters more than manual control ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11246810131625
### Getting Started **Endpoint** * * `model` β€” `"Wonder"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 128 MP * `output` β€” 128 MP ### Examples
Cover image
Click to view/files/4eOracwbn652V1c63k5ghttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-bitnik-31047866-before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-bitnik-31047866-cloud-wonder-6x-after.jpg&src2label=After&zoom=1
Click to view/files/zY78ryJe3yt93P4dVPdjhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-mahmoud-elbakstani-2151329526-31629949-before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-mahmoud-elbakstani-2151329526-31629949-cloud-after.jpg&src2label=After&zoom=1
# Wonder 2 The most advanced generative realism model for challenging images ### Model Overview **Wonder 2** is the second-generation Wonder model and the most advanced realism-focused image enhancement model in the family. It is designed to handle extremely challenging, low-resolution images and produce outputs that look clean, natural, and professional. Wonder 2 restores sharper, more natural detail across the image, resolving plasticky or airbrushed artifacts to produce clean, realistic results. It recovers skin texture, facial features, hair, fabric, and environmental detail while minimizing artifacts and avoiding unnecessary changes to the source during upscaling. ### Key Capabilities * Second-generation generative enhancement for difficult or low-quality images * Restores sharper, more natural detail with strong artifact prevention * Preserves text, logos, and fine details when source quality allows ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11246810131625
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/enhance-gen/async]() * `model` β€” `"Wonder 2"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `pre_downscale`: int, `1` <= x <= `4`, default = `1` * Control pre-downscaling for false resolution images * `color_correction`: bool, default = `False` * Whether to use color correction during post-processing ### Examples
Cover image
Click to view/files/eTCu0PWoCxs8JhbKjG3o
Click to view/files/rkyhx0fMTfIKxfI5j4Xjhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/api-docs-media/pexels-lance-reis-255748881-before.webp&src1label=Original&src2=https://downloads.topazlabs.com/web-assets/api-docs-media/pexels-lance-reis-255748881-after.webp&src2label=Wonder+2&zoom=1.5
# Wonder 3 Most advanced generative realism model for upscaling images ### Model Overview **Wonder 3** is an updated generative upscaling model designed to deliver significantly higher quality results with more natural detail and improved realism across a wide range of image types. It supports both high-quality inputs and heavily degraded or compressed images, with selectable Low, Medium, and High enhancement levels for greater control across varying input conditions. Wonder 3 performs across all resolution levels and is well suited for portraits, landscapes, wildlife, and complex textures such as fabrics, metallics, feathers, and skin. It also improves on Wonder 2 by resolving challenging edge cases and reducing the plasticky appearance and artifacts seen in earlier versions. ### Key Capabilities * Higher quality results with more natural detail and improved realism. * Handles both high-quality inputs and heavily degraded images with consistent performance. * Preserves text, logos, and fine details when source quality allows. * Multi-level enhancement control for adjusting strength across a range of input conditions. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11123457813
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/enhance-gen/async]() * `model` β€” `"Wonder 3"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `enhancement_strength` β€” `"high"`, `"medium"` , `"low"` ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fbird_wonder3_before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fbird_wonder3_after.jpg&src2label=After&zoom=1.0/files/cFBYtnM9d67ZuCjyv3Lc
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fperson_wonder3_before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fperson_wonder3_after.jpg&src2label=After&zoom=1.0/files/H7YiwrvKmK3QHWuSs5tj
# Wonder 3.5 β€” New! Highest-quality generative upscaling for images with greater detail, precision, and realism ### Model Overview **Wonder 3.5** is an updated generative upscaling model designed to deliver higher levels of detail, precision, and natural realism across a wide range of image types. It supports both high-quality inputs and heavily degraded or compressed images, with selectable Low, Medium, and High enhancement levels for greater control across varying input conditions. Building on Wonder 3, Wonder 3.5 produces finer detail with fewer repetitive patterns and improved handling of visual noise. It also delivers greater precision when enhancing structured graphics such as tables and charts, while maintaining strong performance across portraits, landscapes, wildlife, and complex textures. ### Key Capabilities * Higher-quality results with increased detail and improved realism. * Transformative enhancement for low-resolution and compressed photos, with improved detail and text clarity. * Fewer repetitive patterns and improved handling of visual noise. * Greater precision for tables, charts, and other structured graphics. * Low, Medium, and High enhancement controls for a range of input conditions. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11123457813
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/enhance-gen/async]() * `model` β€” `"Wonder 3.5"` **Model-Specific Parameters** * `enhancement_strength` β€” enum (optional), default `"high"` * Enhancement strength (low, medium, high) * `grain` β€” boolean (optional), default `false` * Whether to add grain to the output * `grain_density` β€” number (optional), default `0.5` * Intensity of the grain effect (0.0 to 1.0) * `grain_model` β€” string (optional), default `"silver"` * Grain model: 'silver', 'gaussian', 'grey' * `grain_size` β€” number (optional), default `1.0` * Size of the grain particles (1 to 5) * `grain_strength` β€” number (optional), default `0.5` * Strength of the grain effect (0.0 to 1.0) * `input_height` β€” integer (optional), default `null` * Input image height in pixels * `input_width` β€” integer (optional), default `null` * Input image width in pixels * `output_height` β€” integer (optional), default `null` * Output image height in pixels * `output_width` β€” integer (optional), default `null` * Output image width in pixels ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F019f5d41-1fa8-77e9-8a42-934e47622648.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F019f5d41-1fa8-77e9-8a42-934e47622648-wonder3.5.jpg&src2label=After&zoom=1/files/oMqnIhGnU48TDwhJY2BU
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-tim-yisa-1040794498-20452012.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-tim-yisa-1040794498-20452012-wonder3.5.jpg&src2label=After&zoom=1/files/Ijt4gxU9fAEJvRognH4B
Click to viewhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/model-examples/bella-vita-skai-aquatic.jpg&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/bella-vita-skai-aquatic-wonder3.5.jpg&src2label=After&zoom=1/files/AQ3GplzKg453ZqwFseyP
# Standard Max High-quality precision upscaling with broader accessibility ### Model Overview **Standard Max** is a generative model that delivers high-quality, natural results while remaining efficient enough to run on a wide range of devices. It achieves detail and realism comparable to generative upscaling models, without the heavy hardware requirements or long processing times typically associated with them. Standard Max delivers strong results across all image types and resolutions, and is especially effective on low-resolution images where it restores photorealistic detail with clean textures and minimal artifacts. It also performs reliably on medium and high-quality sources, making it a versatile and dependable choice for everyday upscaling. ### Key Capabilities * High-quality, true-to-input upscaling with natural detail * Excellent recovery of detail from low-resolution images * Faster than most image diffusion-based upscaling models ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11246810131625
### Getting Started **Endpoint** * * `model` β€” `"Standard MAX"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 24 MP * `output` β€” 384 MP ### Examples
Cover image
Click to view/files/xsnH9H8vpEYXCaUTRpwxhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-james-frid-81279-16428605.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-james-frid-81279-16428605-topaz-v4-enhance.jpeg&src2label=After&zoom=1
Click to view/files/R2PJkNS9SGE2o9lJ7uyHhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Ffadhil-abhimantra-NScrf13AmqE-unsplash.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Ffadhil-abhimantra-NScrf13AmqE-unsplash-topaz-v4-enhance.jpeg&src2label=After&zoom=1
# Recover 3 Generative diffusion model that excels at recovering rich, natural detail ### Model Overview **Recover 3** is a generative image recovery model designed to reconstruct missing detail in low-resolution, damaged, or out-of-focus images, with a particular strength in restoring realistic facial features and natural textures. Now in its third generation, Recover 3 delivers significantly improved detail reconstruction, texture fidelity, and realism compared to earlier versions. Recover intelligently rebuilds hair, skin, fabric, foliage, and other organic detail where original image information is limited or lost. It is especially effective for old photographs, heavily compressed images, and small or blurry faces, producing results that feel photographic rather than artificial. ### Key Capabilities * Reconstructs missing facial features and fine textures with improved realism and stability over earlier Recover models. * Prioritizes believable skin, hair, and material textures while avoiding over-sharpened or plastic artifacts. * Realistic and Creative recovery options to balance fidelity versus detail generation, depending on source quality. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits11246810131625
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/enhance-gen/async]() * `model` β€” `"Recover 3"` or `"Natural Enhance"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `enhancement_strength`: float, `0.0` <= x <= `10.0`, default = `5.0` **Resolution Limits** * `input` β€” 24 MP * `output` β€” 384 MP ### Examples
Cover image
Click to view/files/kohCG5ZcuZ3wvTVt3QJvhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FArchival-before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FArchival-after-gigapixel-recover%20v3-4x-faceai%20v2.jpg&src2label=After&zoom=1
Click to view/files/msgKaQEHi1WoAVSeOr64https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRecover%20with%20Face%20Recover%20Before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRecover%20with%20Face%20Recover%2002.jpg&src2label=After&zoom=1
# Bloom Creative Upscaling for Images ### Model Family Overview Creative image enhancement models designed to upscale and transform GenAI images, with or without text based prompts {% hint style="info" %} Creative models add new levels of detail that can change objects, identity, and stylization. {% endhint %} ### Key Features * Creatively upscale images made with Al up to 8x with stunning detail. * Control details with text-based prompts. * Next-Gen AI image realism for realistic face and skin detail. ### Pricing This family is priced at 1 credit per 2 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1248121620253250
### Models
Cover image
Bloom 2/files/QQOls1kfA7epZThCh8KN/pages/jE1b4sHeBNKy2wOhioyT
Bloom 1 Creative/files/mVbtsGWLIL0kqpK3vx0D/pages/PzZoYOpwL5VbtlsRYdJU
Bloom 1 Realism/files/EhoGfk5bGkmK7CuSfG82/pages/7J7t4iv1WfsanlL5w8ic
# Bloom 2 β€” New & Improved! Higher-quality creative upscaling for GenAI images with new, reimagined details ### Model Overview **Bloom 2** is a creative generative AI upscaling model designed for native GenAI images, including AI-generated artwork, illustrations, and CG renders. It enhances image quality while introducing new detail, texture, and visual elements, with the ability to subtly refine the source or substantially reimagine it. A Creativity control from 1–10 determines how strongly Bloom 2 transforms the source, from restrained enhancement to more pronounced reinterpretation and newly generated detail. Bloom 2 also includes optional Face Recovery to improve facial and skin detail and reduce the plastic look common in AI-generated images, plus Color Preservation to maintain the source colors while new creative detail is introduced. ### Key Capabilities * Improved creative upscaling for GenAI images with new realistic detail and texture. * Enhanced skin and facial detail for more natural-looking subjects. * Creativity control from 1–10 for subtle enhancement through bold reinterpretation. * Optional Face Recovery and Color Preservation for greater control over final results. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1248121620253250
### Getting Started **Endpoint** * * `"Bloom 2"` **Model-Specific Parameters** * `color_preservation` β€” boolean (optional), default `true` * Whether to enable color preservation * `creativity` β€” integer (optional), default `3` * Creativity level: from 1 (low) to 9 (high) * `grain` β€” boolean (optional), default `false` * Whether to add grain to the output * `grain_density` β€” number (optional), default `0.5` * Intensity of the grain effect (0.0 to 1.0) * `grain_model` β€” string (optional), default `"silver"` * Grain model: 'silver', 'gaussian', 'grey' * `grain_size` β€” number (optional), default `1.0` * Size of the grain particles (1 to 5) * `grain_strength` β€” number (optional), default `0.5` * Strength of the grain effect (0.0 to 1.0) * `input_height` β€” integer (optional), default `null` * Input image height in pixels * `input_width` β€” integer (optional), default `null` * Input image width in pixels * `output_height` β€” integer (optional), default `null` * Output image height in pixels * `output_width` β€” integer (optional), default `null` * Output image width in pixels * `prompt` β€” string (optional), default `""` * Text prompt for generation * `seed` β€” integer (optional), default `2` * Random seed for generation ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGenerated%20Image%20December%2016%2C%202025%20-%2010_17AM%20copy.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGenerated%20Image%20December%2016%2C%202025%20-%2010_17AM-bloom-2.png&src2label=After&zoom=1/files/QQOls1kfA7epZThCh8KN
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcbot_Im_not_able_to_shorten_or_reformat_this_prompt._--chaos__750b9857-acd0-4d8b-b9c9-85f62169eb78_2%20copy.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcbot_Im_not_able_to_shorten_or_reformat_this_prompt._--chaos__750b9857-acd0-4d8b-b9c9-85f62169eb78_2-bloom-2.png&src2label=After&zoom=1/files/Zqe6jpauN7aFVEYwWzqW
# Bloom 1 Creative Creative upscaling for AI generated images and artwork ### Model Overview **Bloom Creative** is a generative AI upscaling model designed for native GenAI images, enlarging AI-generated artwork, illustrations, and CG renders by up to 8Γ— while creatively introducing new detail, texture, and visual elements. Bloom is guided by an optional prompt input and offers adjustable creativity levels, ranging from zero to bold, allowing users to subtly enhance existing detail or introduce significant, dynamic new elements. ### Key Capabilities * Built for native GenAI imagery or artwork that needs creative enhancement * Prompt-based guidance controls style, texture, and creative direction * Scalable creativity enables subtle enhancement or bold transformation ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1248121620253250
### Getting Started **Endpoint** * * `"Bloom"` or `"Reimagine"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `creativity` β€” integer between 1 and 9, default 3 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `seed` β€” integer between 1 and 2000, default 1 * `face_preservation` β€” boolean, default `true` * `color_preservation` β€” boolean, default `true` * `creativity_boost` β€” boolean, default `false` * `grain` β€” boolean, default `false` * Selects whether or not to apply grain. * `grain_model` β€” `"silver rich"`, `"gaussian"`, or `"grey"` *(required if `grain=true`)* * `grain_strength` β€” decimal between 0 and 1, default 0.5 *(required if `grain=true`)* * Adjusts the strength of the grain. * `grain_density` β€” decimal between 0 and 1, default 0.5 *(required if `grain=true`)* * Adjusts the concentration of grain particles within a given pixel. * `grain_size` β€” decimal between 1 and 5, default 1.0 *(required if `grain=true`)* * Adjusts the size of the grain particles. * `mask_uri` β€” string, optional ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAstronaut%202.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAstronaut_bloom_max_4x.png&src2label=After&zoom=1/files/Vx9ntlWFHgenVctoI2dw
# Bloom 1 Realism Realistic and natural detail enhancement for AI-generated images ### Model Overview **Bloom Realism** is an advanced creative upscaling model that removes the plastic, artificial feel of AI-generated images by restoring natural detail and texture across skin, hair, fabrics, metals, and other materials, producing more grounded, believable results. ### Key Capabilities * Upscales native GenAI images by up to 8Γ— while maintaining natural structure and visual coherence * Replaces synthetic-looking surfaces with more realistic texture and material depth * Transforms AI-generated faces and subjects into more believable, lifelike imagery ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1248121620253250
### Getting Started **Endpoint** * * `model` β€” `"Bloom Realism"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `prompt` β€” string, default `""`; max 1024 char * A description of the resulting image you are looking for. **The model responds more to a descriptive statement versus a directive one**. For example, use the phrase "girl with red hair and blue eyes" instead of "change the girl's hair to red and make her eyes blue" * `autoprompt` β€” boolean *(if enabled, ignores value given to `prompt`)* * Whether you want to use our state-of-the-art auto-prompting model to auto-generate a prompt for you. * `texture` β€” integer between 1 and 5 *(recommend 1 at low creativity, 3 at higher creativity)* * Add texture to the image. Recommend setting texture to 1 for at a low creativity level, and 3 for more creative results at a higher creativity level. * `sharpen` β€” decimal between 0 and 1 * Slightly sharpens the image. * `denoise` β€” decimal between 0 and 1 * Reduces noise in the image. * `detail` β€” boolean, default `false` * Adjusts the level of added detail after rendering. * `detail_strength` β€” decimal between 0 and 10 *(required if `detail=true`)* * Sets the strength of the detail. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `creativity` β€” integer between 1 and 4, default 2 * Lower creativity values maintain the highest fidelity to the original image. Higher values take more liberties and provide more creative results for specific details. * `seed` β€” integer between 1 and 2000, default 1 ### Examples
Cover image
Click to view/files/Pj6c2Jkartbu0juZTBDQhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fmagicstudio-art%20-%202025-12-17T162317.939.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fmagicstudio-art%20-%202025-12-17T162317.939_bloom_probably_4x.jpeg&src2label=After&zoom=1
Click to view/files/TGfNb85u7EafZ7T6HpDkhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcbot_a_space_man_in_a_battle_a_futuristic_boho_space_suit_tig_5149553b-4fe7-42e1-b92f-e12b74b96638_0.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcbot_a_space_man_in_a_battle_a_futuristic_boho_space_suit_tig_5149553b-4fe7-42e1-b92f-e12b74b96638_0_bloom_max_6x.png&src2label=After&zoom=1
# Denoise Reduce Noise and Grain in Images ### Model Family Overview Specialized image noise reduction models for reducing noise and graininess while preserving detail. ### Key Features * Eliminate distracting noise caused by low-light conditions * Fix compression while recovering crisp details * Designed to denoise on both processed image formats and RAW images ### Pricing This family is priced at 1 credit per 24 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1111122335
### Models
Cover image
Normal/files/vNDQZizqMCt0qXFhBHzx/pages/jL6VesW3VVw4H3rXnxJi
Strong/files/bEbUsIxPn5xDpZ4PNHrr/pages/15K6E90W2ZrCLGXlwR4J
Extreme/files/Pe1RXm5WatRtfvgRwstN/pages/kovUXPt14tzv7wB5j2ot
# Normal General-purpose noise reduction ### Model Overview **Denoise Normal** is designed for everyday images with low-to-medium noise caused by low-light conditions or compression, preserving detail without over-processing. ### Key Capabilities * Removes common low-light and compression noise * Preserves fine detail and natural texture * For non-RAW images, recommended starting point for denoising ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Normal"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `strength` β€” decimal between 0.01 and 1 * Reduces noise in the image. Too high can remove detail and slightly blur the image. * `minor_deblur` β€” decimal between 0.01 and 1 * Slightly sharpens the image. Counteracts softness caused by noise reduction. * `original_detail` β€” decimal between 0 and 1 * Return texture and fine details lost during noise reduction. Start at low values and slowly increase. * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the denoise. * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the sharpening. * `opacity` β€” decimal between 0 and 1, default 1.0 * Adjust strength of opacity. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/aP2AvMQqB3Cjoqp2vKSphttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-ronyescobarhn-2154459403-33419553.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FDenoise%20Standardpexels-ronyescobarhn-2154459403-33419553-topaz.jpg&src2label=After&zoom=1
# Strong High-noise detail preservation ### Model Overview **Denoise Strong** targets medium-to-high noise levels from very low-light or high-ISO captures, balancing stronger noise reduction with careful detail retention. ### Key Capabilities * Designed for images shot in very low light * Retains more detail than Extreme while reducing heavy noise * For non-RAW images when Normal does not sufficiently clean the image ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Strong"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `strength` β€” decimal between 0.01 and 1 * Reduces noise in the image. Too high can remove detail and slightly blur the image. * `minor_deblur` β€” decimal between 0.01 and 1 * Slightly sharpens the image. Counteracts softness caused by noise reduction. * `original_detail` β€” decimal between 0 and 1 * Return texture and fine details lost during noise reduction. Start at low values and slowly increase. * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the denoise. * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the sharpening. * `opacity` β€” decimal between 0 and 1, default 1.0 * Adjust strength of opacity. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/dCbR8ntDRYEE6ZzJlMnMhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F2-noisy-bird.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F2-noisy-bird-topaz-denoise.jpg&src2label=After&zoom=1
Click to view/files/dhK83pzv4nFgx38gHcOnhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-christian-diokno-1666462-3772817.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FDenoise%20Strongpexels-christian-diokno-1666462-3772817-topaz.jpg&src2label=After&zoom=1
# Extreme Maximum noise removal ### Model Overview **Denoise Extreme** prioritizes removing severe noise and heavy compression artifacts, favoring cleanliness over fine detail retention. ### Key Capabilities * Removes extreme noise and strong compression artifacts * Best suited for severely degraded or internet-sourced images * For non-RAW images with severe noise or heavy compression ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Extreme"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `strength` β€” decimal between 0.01 and 1 * Reduces noise in the image. Too high can remove detail and slightly blur the image. * `minor_deblur` β€” decimal between 0.01 and 1 * Slightly sharpens the image. Counteracts softness caused by noise reduction. * `original_detail` β€” decimal between 0 and 1 * Return texture and fine details lost during noise reduction. Start at low values and slowly increase. * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the denoise. * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the sharpening. * `opacity` β€” decimal between 0 and 1, default 1.0 * Adjust strength of opacity. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-caiquethecreator-2949322.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FDenoise%20Extreme%202pexels-caiquethecreator-2949322-topaz.jpg&src2label=After&zoom=1/files/RkSznMLijVOvm8GAOyi3
# Max Highest-quality denoising with intelligent detail recovery ### Model Overview **Denoise Max** is a next-generation generative denoising model that delivers the highest quality results in the Denoise family, incorporating technology advancements from Wonder 2. It removes noise and grain with significantly reduced artifacts while intelligently sharpening blurry areas without affecting already sharp detail. Denoise Max performs best on medium to high quality images with light noise or structured grain, and excels across a wide range of content including portraits, hazy images, and fine textures such as skin, hair, and small details. ### Key Capabilities * Best-in-class denoising with reduced artifacts and natural results. * Intelligently sharpens blurry areas while leaving already-sharp areas untouched. * Significant reduction in artifacts compared to previous Denoise models. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111222345
### Getting Started **Endpoint** * * `model` β€” `"Denoise Max"`
Endpoint-Specific Parameters * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 *(required if `face_enhancement=true`)* * Choose realistic or creative face recovery. * `subject_detection` β€” `"foreground"`, `"background"`, or `"all"` * Choose where enhancements are applied. * `strength` β€” decimal between 0.01 and 1 * Reduces noise in the image. Too high can remove detail and slightly blur the image. * `minor_deblur` β€” decimal between 0.01 and 1 * Slightly sharpens the image. Counteracts softness caused by noise reduction. * `original_detail` β€” decimal between 0 and 1 * Return texture and fine details lost during noise reduction. Start at low values and slowly increase. * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the denoise. * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * Sets the strength of the sharpening. * `opacity` β€” decimal between 0 and 1, default 1.0 * Adjust strength of opacity. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `strength` β€” decimal from 0.0 to 1.0 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpeople_5_before.jpeg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpeople_5_after.png&src2label=After&zoom=1.0/files/yJrCLHYZeajdMwfBEw6i
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fwildlife_5_before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fwildlife_5_after.png&src2label=After&zoom=1.0/files/SjbLiYWsLd0mvjUKqOvY
# Removal & Cleanup Remove Unwanted Objects and Distractions ### Model Family Overview Specialized image clean up models designed to remove unwanted objects, artifacts, dust, and scratches while preserving natural image structure. ### Key Features * Eliminate the unwanted objects from your images * Automatic removal of dust, scratches, and surface damage ### Pricing This family is priced at 1 credit per 24 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1111122335
### Models
Cover image
Dust & Scratch 2/files/Eq2hUfWqoAyiJ2uEy7xN/pages/0fUWOVzaGYxs44scW6SP
Image Object Matting/pages/S8jyAYwDD4u0tQYE80is
Background Removal/files/VfLAPCrBRiE1djMTRVkq/pages/b8yesuaKRbQ8VvuIbTiD
# Dust & Scratch 2 Automatic blemish cleanup ### Model Overview **Dust & Scratch 2** is a second generation cleanup model that automatically detects and removes dust, specks, and small blemishes across the entire image while better preserving original detail. Designed for film scans, archival photos, and damaged prints. ### Key Capabilities * Automatically identifies and removes dust and minor surface artifacts * Cleans the entire image in a single pass * Ideal for fast cleanup of scanned or archival photos ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Dust-Scratch V2"`
Endpoint-Specific Parameters * `grain` β€” boolean, default `false` * `grain_model` β€” `"silver rich"`, `"gaussian"`, or `"grey"`, default `"silver rich"` *(required if `grain=true`)* * `grain_strength` β€” integer between 0 and 60, default 30 *(required if `grain=true`)* * `grain_density` β€” integer between 0 and 60, default 30 *(required if `grain=true`)* * `grain_size` β€” integer between 1 and 5, default 1 *(required if `grain=true`)* These parameters are **automatically** configured and do not require or accept any selection from the user.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 256 MP * `output` β€” 256 MP ### Examples
Cover image
Click to view/files/h9DdoeHJFJA8eyO6gMWlhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Ftatiana-gonzales-5GJjPvx4G9g-unsplash.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Ftatiana-gonzales-5GJjPvx4G9g-unsplash-topaz-dust.jpg&src2label=After&zoom=1
Click to view/files/m1eTgZlAQuqX1c4Guqd4https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fannie-spratt-7jCUHhhnXAo-unsplash.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fannie-spratt-7jCUHhhnXAo-unsplash-topaz-dust.jpg&src2label=After&zoom=1
# Image Object Matting Eliminate ### Model Overview **Image Object Matting** is a precision extraction model designed to isolate a specific object from an image while preserving fine, semantically-aware edge detail. Rather than separating a single foreground from its background, it identifies a target object based on its semantic meaning and extracts it cleanly, even from complex scenes containing many competing elements. Well suited for detailed compositing and selective editing workflows, it offers greater control in multi-object scenarios than standard background removalβ€”while Background Removal is better suited to images with fewer objects where the entire foreground can be extracted in a single pass, Image Object Matting excels at pulling one chosen object out of a crowded frame. ### Key Capabilities * Accurately extracts a specific object from its background and from other surrounding objects, with precise edge handling. * Supports a select box to designate the target object in scenes containing massive numbers of objects. * Recovers discontinuous regions of the same object based on semantic understanding, keeping separated parts of a single subject intact. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/matting/async]() * `model` β€” `"Object"` **Model-Specific Parameters** * `box` β€” decimal, optional, default = \[0, 0, 1, 1] * The four numbers are the relative left/top/right/top edges, respectively (between 0 and 1). The more precise (tight) the box is, the better the expected result. When no box is passed, it will use \[0, 0, 1, 1] as default (i.e. the entire image), and might misunderstand the target object. {% hint style="info" %} For the highest-quality outputs, we recommend sending images with a single, main object in the foreground. {% endhint %} ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fobject%20input.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fobject%20output.avif&src2label=After&zoom=1/files/Q5eqy7x1Acfo1Eur2wZJ
# Background Removal Remove backgrounds from images ### Model Overview **Background Removal** is a high-quality image segmentation model designed to isolate subjects from their background with precise, production-ready edge handling. It delivers clean extractions across a wide range of photography scenarios, preserving fine details such as hair, soft edges, and semi-transparent elements. Well suited for both creative and high-volume image workflows, including product photography and e-commerce, flexible mask parameters enable further refinement for compositing, design, or downstream use. ### Key Capabilities * Accurately separates subjects from backgrounds with clean, natural edge detail. * Outputs both transparent background images and reusable masks for downstream workflows. * User-adjustable mask controls including shrink/expand, feather, and invert for precise refinement. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/matting/async]() * `model` β€” `"RemoveBG"`
Endpoint-Specific Parameters `mode` β€” Alpha or segmentation, defaults to segmentation * Alpha provides the binary mask of the object * Segmentation provides the cropped object as an RGBA output Any parameters that are not explicitly provided are configured to our default values. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters ### Examples
Cover image
/files/pNJJPBf5CTfF41VyLRd1https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FCow%20copy.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FCow%20copy%20(1).png&src2label=After&zoom=1
/files/vhKllRYo8tXOaMdXg00Nhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-bear-6582763%20copy.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-bear-6582763%20copy%20(1).jpg&src2label=After&zoom=1
# Sharpen Specialized Sharpening for Images and Photos ### Model Family Overview Specialized image sharpening models designed to reduce blur and improve clarity, bringing the subject or entire image into focus. ### Key Features * Superior sharpening for every type of photo * Subject based sharpen with face recovery * Purposely built use-case sharpening models: Standard, Wildlife, Portrait ### Pricing This family is priced at 1 credit per 24 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1111122335
{% hint style="info" %} Sharpen Generative models (e.g. Super Focus 2) are priced at 1 credit per 20 megapixels of output. {% endhint %} ### Models #### GAN Models
Cover image
Standard/files/13P9v4vIaXWz3Vv5LrI5/pages/rrsTZiSLgmYngMWdfP11
Strong/files/e8zPkaUwVjD7CIVGDzO4/pages/N0xrCjwLdIJPLEdq1zBX
Portrait/files/O6MIXfptdo9c2hyhkqdC/pages/cZlF7pYDjUIs17RtnSbd
Wildlife/files/brFCvzTyPm0Y5JNaZWvi/pages/43gWkTsraSHDQd27Mnk6
Natural/files/JM1J4zq3VQ6er59UJ0uB/pages/uAS9g5NKziDcWSwPnKb9
Refocus/files/2w66eaPYCzPCbDNUud3L/pages/o7t7AImcfhwiAE1VzI6k
Motion Blur/files/2adtbslUe0agGDgGIEZk/pages/XA0LG4obCynGU2vXw8Ip
Lens Blur 2/files/U7GNIYyWeEsDn2Y64syA/pages/S45oGNUAWF9KW5gyqkNb
#### Generative Models
Cover image
Super Focus 2/files/m0A5o0newrZXdXZDJSkr/pages/Vv7CJCHslmvPS2h4Paoz
# Standard General-purpose sharpening ### Model Overview **Sharpen Standard** is an all-purpose sharpening model designed for images with mild lens softness or slight motion blur, delivering balanced detail recovery with minimal intervention. Produces clear images with crisp details. Unlike traditional sharpening that darkens or brightens pixel edges. ### Key Capabilities * Optimized for subtle lens blur and light motion blur * Recommended starting point for most photography sharpening workflows ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Sharpen"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * Removes blur from the image. * `opacity` β€” decimal between 0 and 1, default 1.0 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/3DL8qR3Ct3V1To2WLXtFhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-rgsk97-832775.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSharen%20Standardpexels-rgsk97-832775-topaz-sharpen.jpg&src2label=After&zoom=1
# Strong Severe blur recovery ### Model Overview **Sharpen Strong** applies maximum reconstruction strength for severely blurred or out-of-focus images where standard sharpening models are insufficient. ### Key Capabilities * Targets extreme blur and missed focus * Applies significantly stronger correction than Standard * Best used selectively to avoid artifacts ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Strong"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * `opacity` β€” decimal between 0 and 1, default 1.0 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/4u2kXHoKu8GUSP08MSAHhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-fotios-photos-20026560%201.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSharpen%20Strongpexels-fotios-photos-20026560%201-topaz-sharpen.png&src2label=After&zoom=1
# Noise-Aware Sharpen One-click sharpening that separates detail from noise {% hint style="info" %} This model was formerly known as "Auto Sharpen". {% endhint %} ### Model Overview **Noise-Aware Sharpen** is an intelligent automatic sharpening model that uses AI-driven image analysis to evaluate both image quality and scene content before applying sharpening. Unlike traditional sharpening tools that enhance detail and noise equally, the model automatically separates true image detail from digital noise and compression artifacts before intelligently restoring clarity. The result is sharper textures, facial features, fur, and fine edges while preserving the natural character of the original image. By avoiding aggressive edge enhancement, Noise-Aware Sharpen reduces halos, oversharpening, and harsh digital artifacts commonly introduced by conventional sharpening filters. This model is especially effective for low-light, high ISO, wildlife, sports, nighttime, or grain-heavy photography where visible grain or noise is already present or intentionally part of the atmosphere of the shot. It performs best on high-resolution and production-quality imagery where preserving realism and fine detail is critical. ### Key Capabilities * One-click intelligent sharpening with no manual tuning required * Separates image detail from noise before sharpening * Preserves natural texture and realistic image character * Reduces halos, oversharpening, and sharpening artifacts ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Auto Sharpen"` {% hint style="info" %} In order for `"Auto Sharpen"` to be called, all parameters below must be left as null. This is recommended for batch image processing with various image subject types. {% endhint %}
Model-Specific Parameters * `preset` β€” `'normal'`, `'strong'` * Controls the strength of the sharpening `'normal'` for highest fidelity, `'strong'` for extra sharpening to be applied and the most visible results. Defaults to `'normal'`. **Recommended: omit for automatic parameter selection.** * `denoise_strength` β€” (optional) decimal between 0 and 1, default `null` * Amount of noise to remove from the image (for noisy input images, for non-noisy omit). **Recommended: omit for automatic parameter selection**. * `opacity` β€” (optional) decimal between 0 and 1, default `null` * Controls blending with the original, **Recommended: omit for automatic parameter selection**, decrease opacity on very strong sharpening levels (outside the recommended range).
**Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/9335787003.jpg&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/53063746-d55b-4b08-accd-e5d405837452.png&src2label=After/files/DdYTg4zEVoOHM8VYEC5P
Click to viewhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/pexels-mnannapaneni-29388749.jpg&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/82d2c77f-e8a4-4a91-9762-c02b1becb517.png&src2label=After/files/Tifr24mhUi6OoXcW0l8S
Click to viewhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/parker-johnson-MOPTew6XlTA-unsplash.jpg&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/eed144e0-da8b-4d8d-aa82-998f071e8d11.png&src2label=After/files/w5YHQKpoVlZy5qFoHjOJ
# Portrait Detail enhancement for people ### Model Overview **Sharpen Portrait** is trained to enhance fine detail in high-resolution images of people, prioritizing natural skin texture and facial structure. ### Key Capabilities * Optimized for faces and skin detail * Avoids harsh edges and unnatural texture * Best suited for portraits and close-up human subjects ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Portrait"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * `opacity` β€” decimal between 0 and 1, default 1.0 {% hint style="info" %} When calling `"Wildlife"` or `"Portrait"`, If the user does not specify a value for any of the above parameters, it will automatically calculate the optimal settings for sharpening based on the technical quality of the input (effectively the same as calling `"Auto Sharpen"`). {% endhint %} **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/c6B5I3gN79zI19DSoQKXhttps://compare.topazlabs.com/share/image?src1=https://downloads.topazlabs.com/web-assets/model-examples/Portrait%20Sourcepexels-iamikeee-3310695%201-topaz-denoise.png&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/Portraitpexels-iamikeee-3310695%201-topaz-sharpen-denoise.png&src2label=After&zoom=1
# Wildlife Detail recovery for nature imagery ### Model Overview **Sharpen Wildlife** is trained to enhance fine detail in high-resolution wildlife and nature images while preserving organic textures. ### Key Capabilities * Optimized for feathers, fur, scales, and natural patterns * Avoids over-processing delicate detail * Designed for high-resolution nature photography ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Wildlife"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `sharpen_strength` β€” decimal between 0 and 1, default 0.5 * `opacity` β€” decimal between 0 and 1, default 1.0 {% hint style="info" %} When calling `"Wildlife"` or `"Portrait"`, If the user does not specify a value for any of the above parameters, it will automatically calculate the optimal settings for sharpening based on the technical quality of the input (effectively the same as calling `"Auto Sharpen"`). {% endhint %} **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-anacardia-2570085%20(md).jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-anacardia-2570085%20(md)-topaz-upscale-4x-sharpen.jpg&src2label=After&zoom=1/files/5wae2Xyeklf1TVKePw6P
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F694441bec5286c51fe7a2541_photo-wildlife-2-before.webp&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F694441bec5286c51fe7a2541_photo-wildlife-2-before-topaz-denoise-sharpen-upscale.webp&src2label=After&zoom=1/files/VQBFcBzoeAolIiiHCiam
# Natural Texture-preserving sharpening ### Model Overview **Sharpen Natural** is designed for texture-sensitive images where realism is prioritized over maximum sharpness, preserving organic surfaces without introducing artifacts. ### Key Capabilities * Maintains realistic texture and surface detail * Ideal for subtly soft images requiring restrained enhancement * Avoids halos, plastic textures, and over-sharpened edges ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Natural"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `strength` β€” decimal between 0.01 and 1 * `minor_denoise` β€” decimal between 0.01 and 1 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/cEpmtKfBSB3OEWiUwIRNhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-ralph-407274-3156994.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSharpen%20Naturalpexels-ralph-407274-3156994-topaz-sharpen.jpg&src2label=After&zoom=1
# Refocus Micro-detail enhancement ### Model Overview **Sharpen Refocus** enhances micro-detail and fine structure in slightly defocused images, emphasizing texture and small features rather than global sharpness. ### Key Capabilities * Brings out fine lines and subtle texture * Designed for lightly defocused images * Adds clarity without aggressive edge enhancement ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Refocus"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `strength` β€” decimal between 0.01 and 1 * `minor_denoise` β€” decimal between 0.01 and 1 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/sUciWslSL5UtaAD5hn9shttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-aymane-hanni-2148955127-30646395.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-aymane-hanni-2148955127-30646395-topaz-v4-focus-face-denoise.jpg&src2label=After&zoom=1
Click to view/files/JW1d7W8fK5Hd7XqeVMCqhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-rdne-7516464.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-rdne-7516464-topaz-v4-focus-4.jpg&src2label=After&zoom=1
# Motion Blur Motion artifact correction ### Model Overview **Sharpen Motion Blur** is optimized to correct directional streaking and smearing caused by camera shake or subject movement during exposure. ### Key Capabilities * Targets blur caused by motion rather than defocus * Reduces smearing while restoring edge clarity * Best suited for action or handheld captures ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Motion Blur"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `strength` β€” decimal between 0.01 and 1 * `minor_denoise` β€” decimal between 0.01 and 1 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/4dXYOLhj8tVprTi3TOXUhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fshubham-bombarde-aElqlLEBbO0-unsplash.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSharpen%20%20Motion%20Blurshubham-bombarde-aElqlLEBbO0-unsplash-topaz-sharpen.jpg&src2label=After&zoom=1
# Lens Blur 2 Defocus and lens blur correction ### Model Overview **Sharpen Lens Blur 2** is a second-generation model designed to correct optical defocus and lens-related blur with stronger and more consistent results than prior versions. ### Key Capabilities * Targets defocus and lens imperfections rather than motion blur * Delivers consistent sharpening across heavily blurred regions * Effective for high-intensity defocus correction ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Lens Blur V2"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `strength` β€” decimal between 0.01 and 1 * `minor_denoise` β€” decimal between 0.01 and 1 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/sbCpUv1MykG7f6MYEOuthttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSource.png&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAfter.png&src2label=After&zoom=1
Click to view/files/UVfTexOOzhPKl1EU4NGbhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-pixabay-163482.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FLens%20Blur%20pexels-pixabay-163482-topaz-sharpen.jpg&src2label=After&zoom=1
# Super Focus 2 Generative blur recovery for severely blurred images ### Model Overview **Super Focus 2** is a generative AI feature that fixes blur and reconstructs detail in the most stubborn images, providing an alternative solution when traditional sharpening models cannot recover usable results. ### Key Capabilities * Recovers detail from severely blurred or out-of-focus images that other sharpening approaches fail to enhance * Uses generative reconstruction to rebuild edges and textures without introducing halos or excessive noise * Best suited for difficult, single-image recovery cases where faster sharpening methods do not deliver acceptable results ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111222345
### Getting Started **Endpoint** * * `model` β€” `"Super Focus V2"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `detail` β€” decimal between 0 and 1 * Increases details. Too much sharpening can create an unrealistic result. * `focus_boost` β€” decimal between 0.25 and 1 * Use on very blurry images! Focus boost corrects images that are missing detail by downscaling your image then upscaling the results back to the original size. **Resolution Limits** * `input` β€” 256 MP * `output` β€” 256 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-aymane-hanni-2148955127-30646395.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-aymane-hanni-2148955127-30646395-topaz-v4-focus-face-denoise.jpg&src2label=After&zoom=1/files/GxeTWJpW3ia1BrTMDFni
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fannie-spratt-7jCUHhhnXAo-unsplash.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fannie-spratt-7jCUHhhnXAo-unsplash-topaz-dust.jpg&src2label=After&zoom=1/files/Gt8ssanbQJKczaiYNJ4S
# Super Focus 3 Generative blur recovery with selective refinement ### Model Overview **Super Focus 3** is a next-generation model designed to recover detail from severely blurred or out-of-focus images when traditional sharpening methods fall short. It selectively refines only the blurry regions of an image, intelligently preserving already-sharp details while handling variable blur with precision. This results in more natural reconstruction of detail, edges, and textures, with improved fidelity over Super Focus 2, especially on faces and skin. ### Key Capabilities * Selectively enhances blurred areas while preserving sharp regions, handling variable blur with precision. * Produces more natural detail and improved realism, particularly on faces and skin. * Can be applied multiple times for stronger recovery when needed. * Powered by NeuroStream for local performance across a wide range of hardware. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111222345
### Getting Started **Endpoint** * * `model` β€” `"Super Focus V3"`
Endpoint-Specific Parameters * `denoise_strength` β€” decimal between 0 and 1, default 0.5 * Removes noise from the image. * `face_enhancement` β€” boolean * Leverages our face recovery model to enhance faces. * `face_enhancement_strength` β€” decimal between 0 and 1 * Sets the strength of the face recovery. * `face_enhancement_creativity` β€” decimal between 0 and 1 * Choose realistic or creative face recovery. * `subject_detection` β€” `"All"`, `"Foreground"`, or `"Background"` * Choose where enhancements are applied. These parameters should be appended as key-value fields in the form-data request bodies (i.e. alongside the `model`, `output_height`, and `face_enhancement` etc. fields). Any parameters not explicitly provided are **automatically** configured by our auto-parameter model. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 256 MP * `output` β€” 256 MP ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fnyc_1098_alco_fa_dumont_nj_1953_ron_amberger_sfv3_before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fnyc_1098_alco_fa_dumont_nj_1953_ron_amberger_sfv3_after.jpg&src2label=After&zoom=1.0/files/hcDtrEFUXgAycY5EkBh0
Click to viewhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fimg_7271_sfv3_before.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fimg_7271_sfv3_after.jpg&src2label=After&zoom=1.0/files/nUJH3Cyfu6CEqhoUxELR
# Color & Lighting Fix Exposure, Contrast, and Color Balance ### Model Family Overview Specialized image color and lighting models designed to fix exposure and color balance issues, creating well lit images with natural, true to life color. ### Key Capabilities * Automatically corrects lighting and color for natural results. ### Pricing This family is priced at 1 credit per 24 megapixels of output. Below are costs for common outputs.
TextNumber
Output MP148162432405064100
Credits1111122335
### Models
Cover image
Adjust Lighting 2/files/4lcfxIiQK2u3X5vBlJk4/pages/1JCQzylyeWdr9GEQFmIV
Balance Color/files/iKyFhtO42sN3fGeLSUjo/pages/4ko4hmZzW3cAyTpGVP92
Image Colorization/files/v6oP34rb7HakX96iLwhA/pages/GMvRBZcuGg1UdHOGTMOw
# Adjust Lighting 2 Intelligent exposure correction ### Model Overview **Adjust Lighting 2** is a second-generation lighting correction model that automatically improves exposure, contrast, and tonal balance while preserving natural image appearance. ### Key Capabilities * Automatically adjusts exposure and contrast for balanced results * Improves highlight and shadow detail without harsh transitions * Second-generation model with improved consistency and tonal handling ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * [https://api.topazlabs.com/image/v1/lighting/async]() * `model` β€” `"Adjust V2"`
Endpoint-Specific Parameters * `color_correction` β€” boolean * Adjust the vibrance. * `exposure` β€” decimal between 0 and 2 * Adjust the exposure. * `highlight` β€” decimal between 0 and 2 * Adjust prominence of highlights. * `shadow` β€” decimal between 0 and 2 * Adjust prominence of shadows. * `temperature` β€” decimal between 0.01 and 1 * Adjust overall warmth * `opacity` β€” decimal between 0.01 and 1 * Adjust strength of opacity. * `saturation` β€” decimal between 0 and 1, default 0.2 * Adjust saturation. Any parameters that are not explicitly provided are configured to our default values. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * `lab_blend_alpha` β€” decimal between 0 and 1, default 0.6 * `lighting` β€” decimal between 0.5 and 1.5, default 1.0 **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/uxQuUIYgnQTzI9Jww8RLhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-yaroslav-shuraev-8499870.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAdjust%20Lighting%20v1.jpg&src2label=After&zoom=1
Click to view/files/zyvDiDycGzkhP9Rf9EGUhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-n-voitkevich-5425793.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAdjust%20Lighting%20v2%20pexels-n-voitkevich-5425793-topaz-lighting.jpg&src2label=After&zoom=1
# Balance Color Automatic color correction ### Model Overview **Balance Color** automatically corrects color balance and white balance issues to produce natural, visually consistent results across a wide range of images. ### Key Capabilities * Corrects color casts and white balance automatically * Produces natural-looking color without manual grading * Ideal for fast, reliable color correction across diverse imagery ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"White Balance"`
Endpoint-Specific Parameters * `color_correction` β€” boolean * Adjust the vibrance. * `exposure` β€” decimal between 0 and 2 * Adjust the exposure. * `highlight` β€” decimal between 0 and 2 * Adjust prominence of highlights. * `shadow` β€” decimal between 0 and 2 * Adjust prominence of shadows. * `temperature` β€” decimal between 0.01 and 1 * Adjust overall warmth * `opacity` β€” decimal between 0.01 and 1 * Adjust strength of opacity. * `saturation` β€” decimal between 0 and 1, default 0.2 * Adjust saturation. Any parameters that are not explicitly provided are configured to our default values. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/jfNrMIhk5hJoc5rK7dkGhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpexels-100k-makhasette-2160826-3805874.jpg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FBalance%20Color%20pexels-100k-makhasette-2160826-3805874-topaz-color.jpg&src2label=After&zoom=1
# Image Colorization Automatic colorization for black & white images ### Model Overview **Image Colorization** automatically transforms black-and-white and faded images into natural, full-color results using context-aware color mapping. It intelligently assigns realistic hues based on scene content, restoring life to historical photos and grayscale imagery while maintaining a natural, balanced appearance. ### Key Capabilities * Converts black-and-white and faded images into realistic, full-color results. * Automatically selects context-appropriate colors for natural-looking output. * Ideal for restoring archival photos and enhancing historical imagery. ### Model Pricing
TextNumber
Output MP148162432405064100
Credits1111122335
### Getting Started **Endpoint** * * `model` β€” `"Colorize"`
Endpoint-Specific Parameters * `color_correction` β€” boolean * Adjust the vibrance. * `exposure` β€” decimal between 0 and 2 * Adjust the exposure. * `highlight` β€” decimal between 0 and 2 * Adjust prominence of highlights. * `shadow` β€” decimal between 0 and 2 * Adjust prominence of shadows. * `temperature` β€” decimal between 0.01 and 1 * Adjust overall warmth * `opacity` β€” decimal between 0.01 and 1 * Adjust strength of opacity. * `saturation` β€” decimal between 0 and 1, default 0.2 * Adjust saturation. Any parameters that are not explicitly provided are configured to our default values. Extra parameters provided that are not supported are ignored.
**Model-Specific Parameters** * No parameters **Resolution Limits** * `input` β€” 512 MP * `output` β€” 512 MP ### Examples
Cover image
Click to view/files/RY56nbdnSXBKo6S7K266https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpre%20color.jpeg&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FColored.jpeg&src2label=After&zoom=1
# Proteus Precision Video Upscale & Enhancement ### Model Family Overview Essential video enhancement models designed for quality, precision, and control. {% hint style="info" %} Precision models attempt to improve quality without changing the source characteristics. {% endhint %} ### Key Features **Built for the widest range of video sources** * High quality upscaling and enhancement across camera-based footage, CGI, and AI-generated video, with models optimized for both low resolution and high resolution sources. **Clean, natural enhancement without artifacts** * Improve resolution, reduce noise, and remove compression artifacts without introducing artificial edges or altering the character of the footage. **Professional control and format support** * Advanced parameters and dedicated handling for interlaced, telecine, and progressive sources support modern and legacy workflows. **High resolution results with local and cloud workflows** * Scale content up to 8K and beyond using efficient processing on local workstations or cloud-based infrastructure. ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} Gaia 2 (Animation) is roughly 50% cheaper than all other models in this family.\ \ For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Models
Cover image
Proteus/files/kGF83JWhxHAt5u7pybc0
Proteus Natural/files/PP7WKMonSRhKrmVb04uh
Rhea/files/68SJ5w9hFBN31JPb76KM
Theia/files/NZ4uXDkmxpMgipknPjmr
Artemis/files/16H5qBiJ2C36Ahgj1RjS
Dione/files/HiWSQKwi49XdzZVP7cQm
Gaia/files/u0sIhX9UhL9vrmNXBn28
Gaia 2 (Animation)/files/APM6sPIeaC0sfTASR0qW/pages/axF7x6GUTwC1cGGZotpP
Iris/files/wldQP0K9Y8p42p4hZRcF
# Proteus The default choice for video enhancement ### Model Overview **Proteus** delivers high quality results across a wide range of sources and is recommended as the default model for most common video upscaling projects. A versatile, general purpose enhancement model for upscaling, denoising, and sharpening a wide range of low to medium quality video sources. Proteus performs especially well on low to medium quality footage, including old, grainy, or heavily compressed video. ### Key Capabilities * General purpose and most recommended video enhancement model * Effective on both progressive and interlaced footage, commonly used to upscale legacy low resolution content to 4K * Offers modifiable parameters for fine tuning results, including controls for compression recovery, detail enhancement, sharpening, noise reduction, dehalo, and anti aliasing or deblur ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"prob-4"` **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view/files/kGF83JWhxHAt5u7pybc0https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSC_RipAq_001_EPRIII_LQ2.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSC_RipAq_001_EPRIII_LQ2_1_prob4.mp4&src2label=After&zoom=1
Click to view/files/MGibasuJtWp1C6I2erc1https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_hyper-real_Astronaut_in_space_waving_at_an_alien__0ac3e91e-399a-4309-8780-a6b8b7c9466b_1.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_hyper-real_Astronaut_in_space_waving_at_an_alien__0ac3e91e-399a-4309-8780-a6b8b7c9466b_1_prob4.mp4&src2label=After&zoom=1
# Proteus Natural Next-generation natural enhancement ### Model Overview **Proteus Natural** is an update to the popular Proteus model, designed to eliminate over sharpening and over enhancement that can occasionally occur during upscaling. This next generation refinement delivers a more natural, softer output while preserving texture and source character. Proteus Natural reduces sharpening halos, aliasing, and background distortion, producing clean, stable upscales across a wide range of video sources and supporting both local and cloud workflows. ### Key Capabilities **Second generation refinement of Proteus** * Designed for a more natural, restrained enhancement compared to the original Proteus model. **Cleaner results with fewer artifacts** * Reduces halos, aliasing, and facial distortion, especially in small details and background faces. **Stable, conservative upscaling for real-world footage** * Avoids over sharpening or texture exaggeration and integrates well into multi-step enhancement workflows ### Pricing | Duration | 360p β†’ 720p | 540p β†’ 1080p | 720p β†’ 1440p | 1080p β†’ 4K | | -------- | ----------- | ------------ | ------------ | ---------- | | **1s** | 1 | 1 | 1 | 1 | | **5s** | 1 | 1 | 2 | 3 | | **10s** | 1 | 2 | 3 | 5 | | **1m** | 4 | 8 | 13 | 29 | | **5m** | 17 | 37 | 65 | 145 | | **10m** | 33 | 73 | 129 | 290 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator).\ \ Note: `pnat-1` is a 2x upscale only model. Example upscale factors and durations are displayed above. {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"pnat-1"` **Model-Specific Parameters** * No parameters {% hint style="info" %} Proteus Natural only uses a `2.0` upscale factor. {% endhint %} ### Examples
Cover image
Click to view/files/PP7WKMonSRhKrmVb04uhhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpn1-before-opt.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fpn1-after-opt.mp4&src2label=After&zoom=1
# Rhea High-fidelity 4Γ— upscaling for fine detail ### Model Overview **Rhea** is a high fidelity enhancement model designed for 4Γ— upscaling of organic textures and fine detail, delivering clean, controlled sharpness while preserving natural structure. Rhea blends the general enhancement strengths of Proteus with the facial recovery capabilities of Iris to recover fine detail and faces from lower resolution sources such as 480p footage. It operates natively at a 4Γ— scale and is best suited for workflows where maximum detail preservation is prioritized over render speed. ### Key Capabilities * Optimized for high quality 4Γ— upscaling of organic textures and fine detail * Preserves faces, text, and small structures with natural looking sharpness * Best suited for clean or lower resolution sources where fidelity is prioritized over speed ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"rhea-1"` **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FTRex-Interview-Cam1_1_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FTRex-Interview-Cam1_1_rhea1.mp4&src2label=After&zoom=1/files/68SJ5w9hFBN31JPb76KM
Click to viewhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6274900_Surreal-Painted-Illusion-Monster_By_Gundars_Magone_Artlist_HD.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6274900_Surreal-Painted-Illusion-Monster_By_Gundars_Magone_Artlist_HD_rxl1.mp4&src2label=After&zoom=1/files/wIZD3oVKN7pDMJ5KqfSf
# Theia Manual clarity and detail control ### Model Overview **Theia** is a clarity focused enhancement model designed to sharpen and enhance detail in video footage while controlling noise. It is well suited for situations where additional detail is needed and a hands on approach to tuning results is preferred. Theia provides granular manual control through three adjustable parameters and includes two fine tuning modes. Fine Tune Fidelity prioritizes stable, consistent detail with reduced artifacts, while Fine Tune Detail aggressively enhances detail on a per frame basis and may introduce subtle variation between frames. ### Key Capabilities * Clarity focused sharpening and detail enhancement with noise control * Granular manual adjustment using three core parameters * Two fine tuning modes, **Theia Fine Tune Fidelity** (for stable results) and **Theia Fine Tune Detail** (for aggressive detail extraction) ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” * `"thd-3"` (Theia Fine Tune Detail) * `"thf-4"` (Theia Fine Tune Fidelity) **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view
Fine Tune Detail		/files/tQSfJ29GJavxZu5akhaqhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F219153_small.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F219153_small_thd3.mp4&src2label=After&zoom=1
Click to view
Fine Tune Fidelity		/files/Qu9pmin6iLMZre1lKMWKhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F219153_small.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F219153_small_thf4.mp4&src2label=After&zoom=1
# Theia Fine Tune Detail ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"thd-3"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Theia Fine Tune Fidelity ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"thf-4"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis Balanced denoise and sharpening ### Model Overview **Artemis** is a general enhancement model that balances detail enhancement with noise and artifact reduction. It is designed to handle low, medium, and high quality footage with a range of common issues, including haloing, aliasing, and compression artifacts. ### Key Capabilities * General purpose denoise and sharpen model * Offers multiple tuned variants for different footage conditions * Available variant include **High Quality**, **Medium Quality**, **Low Quality**, **Medium Halo**, **Strong Halo**, and **Aliasing or Moire** ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” * `"ahq-12"` (Artemis HQ) * `"alqs-2"` (Artemis MQ) * `"alq-13"` (Artemis LQ) * `"amqs-2"` (Artemis Medium Halo) * `"amq-13"` (Artemis Strong Halo) * `"aaa-9"` (Artemis Aliasing / Moire) **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view
Artemis HQ		https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short_ahq12_HQ.mp4&src2label=After&zoom=1/files/r3eTWEKlR84hLmcxN2y7
Click to view
Artemis MQ		https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short_amq13_MQ.mp4&src2label=After&zoom=1/files/QmIQfs7RsjV1ctqD9XBP
Click to view
Artemis LQ		https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F8mm_Nature_EPRIII_1_tvai_short_alq13_LQ.mp4&src2label=After&zoom=1/files/ZCfRfDWGzL2DmEEzE76z
Click to view
Artemis Medium Halo		https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6402837_Cloth-Covered-Character-Abstract_By_Murad_Muradov_Artlist_4K_1.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6402837_Cloth-Covered-Character-Abstract_By_Murad_Muradov_Artlist_4K_1_amqs2.mp4&src2label=After&zoom=1/files/16H5qBiJ2C36Ahgj1RjS
Click to view
Artemis Aliasing Moire		https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_Masquerade_done_in_a_2D_animation_from_the_90s_-_ad6b7fb0-9033-420f-844d-724c946d2d91_2.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_Masquerade_done_in_a_2D_animation_from_the_90s_-_ad6b7fb0-9033-420f-844d-724c946d2d91_2_aaa9.mp4&src2label=After&zoom=1/files/4FiGIWC3HGvykg0BlHBl
Click to view
Artemis Strong Halo		https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FVHS-C_SFCity_HomeVideo_EPRIII_CLIP.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FVHS-C_SFCity_HomeVideo_EPRIII_CLIP_alqs2.mp4&src2label=After&zoom=1/files/wGopHGzPl7oniwZYQHP8
# Artemis Aliasing / Moire ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"aaa-9"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis Low Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"alq-13"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis Medium Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"alqs-2"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis High Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"ahq-12"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis Medium Halo ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"amqs-2"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Artemis Strong Halo ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"amq-13"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Dione Deinterlacing and legacy video conversion Model Overview **Dione** is designed for deinterlacing and upscaling interlaced video formats, converting sources such as 480i, 576i, 1080i, and legacy analog or DVD footage into a high quality progressive result. ### Key Capabilities * Purpose built for interlaced video workflows * Includes specialized variants tuned for different source types * Available variants include **Dione DV** for digital video, **Dione TV** for analog broadcast sources, and **Dione Dehalo** for reducing edge artifacts and fringing ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” * `"ddv-3"` (Dione DV) * `"dtv-4"` (Dione TV) * `"dtd-4"` (Dione Robust) * `"dtvs-2"` (Dione Dehalo) * `"dtds-2"` (Dione Robust Dehalo) **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view
Dione DV		/files/v7JPnvQQ1lEPr9DCIbhNhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGuerrilla-NTSC-Interlaced-before_short_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGuerrilla-NTSC-Interlaced-before_short_ddv3.mp4&src2label=After&zoom=1
Click to view
Dione TV		/files/DAOaCCauRSeMFj8QtQqshttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_Angel_short_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_Angel_short_dtv4.mp4&src2label=After&zoom=1
Click to view
Dione Robust		/files/OORscvLyO7SzctDOU38nhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_VHSC_HL2_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_VHSC_HL2_dtd4.mp4&src2label=After&zoom=1
Click to view
Dione Dehalo		/files/515vPyvQOftn9LfBguq2https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_VHSC_HL_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_VHSC_HL_dtvs2.mp4&src2label=After&zoom=1
Click to view
Dione Robust Dehalo		/files/pF0EZqT7uWFuGk93vA78https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FB-Roll-02_RexJaw_int.mov&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FB-Roll-02_RexJaw_int_dtds2.mp4&src2label=After&zoom=1
# Dione DV ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"ddv-3"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Dione TV ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"dtv-4"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Dione Robust ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"dtd-4"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Dione Dehalo ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"dtvs-2"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Dione Robust Dehalo ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"dtds-2"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Gaia Refinement for high-quality CGI and animation ### Model Overview **Gaia** is designed to upscale and refine high quality CGI and animation sources. It assumes the input footage is already clean and well rendered, focusing on subtle refinement rather than heavy artifact removal. Gaia is not intended for heavily compressed or damaged footage and is best used as a final step to increase resolution while preserving the original source characteristics. ### Key Capabilities * Optimized for high fidelity CGI and animation content * **Gaia High Quality (HQ)** improves fine detail and aliased edges in already clean sources * **Gaia Computer Generated (CG)** is well suited for animation, linework, and stylized imagery ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” * `"gcg-5"` (Gaia CG) * `"ghq-5"` (Gaia HQ) **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view
Gaia CG		/files/u0sIhX9UhL9vrmNXBn28https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F259801_Activity-Sport-Girl-Gymnast_By_Serafima_Serafimova_Artlist_HD_1.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F259801_Activity-Sport-Girl-Gymnast_By_Serafima_Serafimova_Artlist_HD_1_gcg5.mp4&src2label=After&zoom=1
Click to view
Gaia HQ
# Gaia 2 (Animation) Next-generation frame-by-frame 2Γ— upscaling for animation ### Model Overview **Gaia 2** is a 2x upscaling model designed specifically for animation and frame-based sources. Unlike traditional video enhancement models that blend frames for temporal smoothness, Gaia 2 processes each frame independently to preserve the intended look of hand-crafted animation and avoid interpolation artifacts. It is best suited for increasing the resolution of clean sources such as stop motion, traditional animation, and motion graphics, with secondary use on high-quality live action plates where frame independence is required. ### Key Capabilities * Improved fidelity, quality, and speed compared to original Gaia model * Frame-by-frame processing preserves original source intent without temporal blending * Supports high-resolution image sequences, including EXR, for integration into VFX and animation workflows ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 300 | 100 | {% hint style="info" %} Gaia 2 is priced at roughly half the price of Gaia CG / HQ for shorter videos.\ \ The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `ganim-1` **Model-Specific Parameters** * No parameters ### Examples
Cover image
Click to view/files/APM6sPIeaC0sfTASR0qWhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F482656_Clock%20Man%20Cartoon%20Tiny%20People_By_Alex_Grigg_Artlist_HD_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F482656_Clock%20Man%20Cartoon%20Tiny%20People_By_Alex_Grigg_Artlist_HD_ganim1.mp4&src2label=Gaia%202&zoom=1
Click to view/files/02BfafNV3Y7EHuxSfETDhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F760257_Victory%20Anime%202d%20Sunset_By_David_Octane_Artlist_4K.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F760257_Victory%20Anime%202d%20Sunset_By_David_Octane_Artlist_4K_ganim1.mp4&src2label=Gaia%202&zoom=1
# Gaia CG ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"gcg-5"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Gaia High Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"ghq-5"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Iris Face recovery for degraded footage ### Model Overview **Iris** is a face focused enhancement model designed to recover facial detail in low to medium quality footage. It is optimized for footage where faces are degraded due to noise, compression, or interlacing. Iris performs best on challenging sources such as archival material, broadcast footage, or heavily compressed video. ### Key Capabilities * Specialized face recovery for older or degraded footage * Works with both progressive and interlaced sources * This model has been specifically trained for low quality (**LQ**) and mid quality (**MQ**) input videos. ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” * `"iris-3"` (Iris Low Quality) * `"iris-2"` (Iris Medium Quality) **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view
Iris LQ		/files/bidSDnh5svYe77CSjvxIhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FIris_Face_before.webm&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FIris_Face_after.webm&src2label=After&zoom=1
Click to view
Iris MQ		/files/wldQP0K9Y8p42p4hZRcFhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGuerrilla-NTSC-Interlaced-before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FGuerrilla-4k-iris3.mp4&src2label=After&zoom=1
# Iris Low Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"iris-3"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Iris Medium Quality ### Model Overview ### Key Capabilities ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"iris-2"` **API Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Click to view
Click to view
# Starlight Generative Video Upscale & Enhancement ### Model Family Overview Advanced diffusion based video enhancement models delivering high quality restoration of difficult archival footage and enhancement of modern GenAI video. {% hint style="info" %} Generative models improve video by intelligently adding detail and texture while preserving artistic intent. {% endhint %} ### Key Features **Restore and elevate challenging video sources** * Recover detail, stability, and texture from degraded archival footage and low quality sources, scaling results cleanly to 4K and beyond. **Enhance GenAI video while preserving creative intent** * Predictive, diffusion-based enhancement improves clarity, consistency, and realism without altering the original visual style or structure. **Natural detail and facial realism** * Refines face detail and skin tones while reducing synthetic or β€œplastic” artifacts common in generative video outputs. **Flexible processing: cloud or local** * Starlight Mini and Starlight Sharp are specialized variants optimized for high-quality local rendering. ### Pricing | Model | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------------------------------------------------------------- | ------------------------- | ---------------------- | | [`Starlight Precise 1`](/video-models/starlight/starlight-precise-1-deprecated) | 10 | \~6 | | [`Starlight Precise 2`](/video-models/starlight/starlight-precise-2-deprecated) | \~26 | \~12 | | [`Starlight Precise 2.5`](/video-models/starlight/starlight-precise-2.5) | \~26 | \~12 | | [`Starlight HQ`](/video-models/starlight/starlight-hq) | \~26 | \~12 | | [`Starlight Mini`](/video-models/starlight/starlight-mini) | \~26 | \~12 | | [`Starlight Sharp`](/video-models/starlight/starlight-sharp) | \~26 | \~12 | | [`Starlight Fast 1`](/video-models/starlight/starlight-fast-1-deprecated) | \~52 | \~24 | | [`Starlight Fast 2`](/video-models/starlight/starlight-fast-2) | \~52 | \~24 | {% hint style="info" %} The above pricing is for our "Quality" models. "Fast" models are priced at 50% of the "Quality" models.\ \ For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Models #### "Quality" Models
Cover image
Starlight Precise 1/files/tMHN6SSQDy54ougVwdU7/pages/NudnxBPiZa0kJFpSKXBI
Starlight Precise 2/files/aBXrkarP9NCESPBgaDQG/pages/aL31hOSUmaDJyjy6MMLU
Starlight HQ/files/n6qzyAColEs7cM0GqDnk/pages/L0rbDpkCO85wqV0xG96q
Starlight Mini/files/JsSLXdjHwBRtQLcciUGP/pages/p6XbRO3Xuv2zktU7q6X9
Starlight Sharp/files/5Aolw92pIhZuz5dow2mz/pages/16zkswHnIFJ3E7RftDty
#### "Fast" Models
Cover image
Starlight Fast 1/files/TVrG25BOq0Pc2N6ZYVcO/pages/9GClaqGsMc9NIkizhT3K
Starlight Fast 2/files/eP7nHtzTtTTxOPIwXvp5/pages/T9fXClXyo1deZmDKBkoP
# Starlight Precise 1 (Deprecated) Restore footage once considered impossible with fully automatic diffusion enhancement ### Model Overview **Starlight Precise 1** is the original diffusion-based video enhancement model and the first of its kind designed specifically for video. Originally developed as Project Starlight, it was created to enhance footage previously considered impossible to restore, including degraded film and low resolution GenAI video. Precise 1 is a generative diffusion model that intelligently improves detail, temporal consistency, and structure while preserving artistic intent, performing all enhancement automatically without manual controls. ### Key Capabilities * First ever diffusion model purpose built for video enhancement * Transforms degraded, low resolution footage into clean, consistent HD or 4K results * High quality, automatic enhancement with no sliders or manual tuning required ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 10 | 6.0241 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"sl-1"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 9000 * `video_profile` β€” string, optional * `video_bit_depth` β€” integer, optional * `video_codec` β€” string, optional ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_Steampunk_Male_robot_puts_a_wedding_ring_on_the_f_0e22ab34-3c17-43bb-abde-febd49842527_0-1.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fu5739975918_Steampunk_Male_robot_puts_a_wedding_ring_on_the_f_0e22ab34-3c17-43bb-abde-febd49842527_0-1-_starlight.mp4&src2label=After&zoom=1/files/3vaIzuI6RQhrjOBww2Jx
Click to viewhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FTheScarletPimpernel_001.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FTVAI_Starlight_TheScarletPimpernel_001_v001.mp4&src2label=After&zoom=1/files/72cQCYz4qYBRGvzsHfYh
# Starlight Precise 2 (Deprecated) Bring realism to GenAI video with natural faces, skin tones, and stable motion ### Model Overview **Starlight Precise 2** is a second generation diffusion video model designed to deliver more natural faces and skin tones for native GenAI video sources. It prioritizes realism and quality while preserving artistic intent. Precise 2 intelligently refines facial detail, skin texture, and structure. Using a single frame diffusion architecture, it reduces ghosting and instability in fast moving, inconsistent, or heavily compressed footage, resulting in improved clarity and temporal consistency. ### Key Capabilities * Restores natural facial detail and skin tones while minimizing synthetic or β€œplastic” artifacts * Best choice for enhancing GenAI video while preserving creative intent and visual structure * Delivers improved stability and detail recovery for difficult or inconsistent footage ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 26.0417 | 11.9179 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slp-2"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 450 * `creativity` β€” `"low"`, `"middle"`, or `"high"`, optional * `is_optimized_mode` β€” boolean, default true * `enable_clc` β€” boolean, default true * `video_profile` β€” string, optional * `video_bit_depth` β€” integer, optional * `video_codec` β€” string, optional ### Examples
Cover image
Click to view/files/pALMATVgVCZoRQzjCNUshttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSchool_Kling_Before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FSchool_Kling_Precise_Starlight_Precise_2.mp4&src2label=After&zoom=1
Click to view/files/aBXrkarP9NCESPBgaDQGhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FShip%20Source%201.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FShip%201%204k%20SLP%202.mp4&src2label=After&zoom=1
# Starlight Precise 2.5 Improved realism for AI-generated video with enhanced faces, texture detail, and text clarity ### Model Overview **Starlight Precise 2.5** is a diffusion video enhancement model designed to improve realism in AI-generated video by reducing plastic or artificial artifacts. Building on Precise 2, it enhances facial detail while improving fabrics, materials, and the clarity of text, labels, and logos. Precise 2.5 is well suited to upscale and enhance AI-generated footage that already has strong composition and structure but appears soft or slightly artificial. It also performs well on archival content where sufficient visual information exists, such as digital video footage from the 2000s onward. ### Key Capabilities * Improved realism for AI-generated video with more natural faces, materials, and textures * Enhanced rendering of text, labels, and fine detail for higher fidelity results * Broad applicability across GenAI and modern archival footage with consistent, stable outputs ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 26.0417 | 11.9179 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slp-2.5"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 9000 * `input_frame_rate` β€” number, optional * `input_height` β€” integer, optional; default 1080 * `input_width` β€” integer, optional; default 1920 * `output_height` β€” integer, optional; default 1080 * `output_width` β€” integer, optional; default 1920 * `video_bit_depth` β€” integer, optional * Bit depth (e.g., 8, 10, 12, 16) * `video_profile` β€” string, optional * Video profile (e.g., `'420'`, `'422'`, `'444'`) * `video_codec` β€” string, optional * Video codec (e.g., `'ffv1'`, `'prores'`, `'vp9'`) ### Examples
Cover image
Click to view/files/cdmc91VVIOBBLYaY2SjXhttps://compare.topazlabs.com/share/video/?src1=https%3A%2F%2Ftopazlabs.s3.us-east-1.amazonaws.com%2Fweb-assets%2Fmodel-examples%2Fvideo_21_veo3.1.mp4&src1label=Source&src2=https%3A%2F%2Ftopazlabs.s3.us-east-1.amazonaws.com%2Fweb-assets%2Fmodel-examples%2Fvideo_21_veo3.1_slp2.5.mp4&src2label=SLP%202.5&zoom=1&view=slider
Click to view/files/XIAmyX4lRMycqTalpTRdhttps://compare.topazlabs.com/share/video/?src1=https%3A%2F%2Ftopazlabs.s3.us-east-1.amazonaws.com%2Fweb-assets%2Fmodel-examples%2Fvideo_45_veo3.1.mp4&src1label=Source&src2=https%3A%2F%2Ftopazlabs.s3.us-east-1.amazonaws.com%2Fweb-assets%2Fmodel-examples%2Fvideo_45_veo3.1_slp2.5.mp4&src2label=SLP%202.5&zoom=1&view=slider
# Starlight HQ Maximum quality generative enhancement for modern high-resolution video ### Model Overview **Starlight HQ** is a high quality enhancement model designed for modern, high resolution video sources. It delivers a strong balance of detail and sharpness while preserving the visual intent of the original footage. Unlike restoration focused models such as Starlight Mini, HQ is optimized for clean progressive video and larger source resolutions. It supports inputs from 480p through 4K and can render native 4K outputs, making it well suited for modern digital camera footage and high resolution finishing. **Starlight HQ** can run locally in Topaz Video or in the cloud via API. For local processing, the model uses a larger architecture that prioritizes visual fidelity over speed and requires an NVIDIA GPU with at least 10GB of VRAM, with 12GB or more recommended. ### Key Capabilities * High fidelity diffusion enhancement for modern digital camera sources * Supports larger inputs up to 4K with native 4K output * Ideal for high resolution workflows where maximum visual quality is the priority ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 26.0417 | 11.9179 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slhq-1"` **Model-Specific Parameters** * `start_idx` β€” integer, default 0 * `end_idx` β€” decimal, default 1000000.0 * `upscaling_factor` β€” decimal, default 1.0 * `low_sharpness` β€” boolean, default false * `keep_original` β€” boolean, default false * `ffmpeg_encoding` β€” string, optional * `ffmpeg_preproc_filters` β€” string, default `""` ### Examples
Cover image
Click to view/files/psLCql2XE0tL5ThyblSlhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6080099_Wild%20Horse%20Roadside%20Fence_By_Yuval_Aloni_Artlist_4K_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6080099_Wild%20Horse%20Roadside%20Fence_By_Yuval_Aloni_Artlist_4K_slhq.mp4&src2label=Starlight%20HQ&zoom=1
Click to view/files/n6qzyAColEs7cM0GqDnkhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6341427_Elderly%20Couple%20Christmas%20Eve_By_Kristian_Ozer_Kettner_Artlist_HD.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6341427_Elderly%20Couple%20Christmas%20Eve_By_Kristian_Ozer_Kettner_Artlist_HD_slhq.mp4&src2label=Starlight%20HQ&zoom=1
# Starlight Mini Powerful local diffusion restoration for archival and interlaced footage ### Model Overview **Starlight Mini** is the first local diffusion model for video enhancement, delivering the core strengths of Starlight technology, optimized for desktop workflows. It enables diffusion based restoration and enhancement without relying on cloud processing. Mini is currently the most powerful diffusion-based video enhancement available for local desktop use. Starlight Mini is well suited for degraded and archival sources, including 8mm and 16mm film, MiniDV, and standard definition video with automatic deinterlacing. Its output emphasizes natural texture and motion consistency, helping reduce flicker, banding, and overly harsh detail. ### Key Capabilities * First and most powerful diffusion based video enhancement model available for local desktop processing * Ideal for restoring degraded, archival, and low resolution footage that challenges traditional models * Produces natural, stable results with reduced flicker, banding, and background artifacts ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 26.0417 | 11.9179 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slm-1"` **Model-Specific Parameters** * `start_idx` β€” integer, default 0 * `end_idx` β€” decimal, default infinity * `upscaling_factor` β€” decimal, default 1.0 * `ffmpeg_encoding` β€” string, optional * `ffmpeg_preproc_filters` β€” string, default `""` ### Examples
Cover image
Click to view/files/JsSLXdjHwBRtQLcciUGPhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fstarlight-crowd-before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fstarlight-crowd-before_Precise_Starlight_Mini.mp4&src2label=After&zoom=1
# Starlight Sharp Fast local restoration with sharper detail for clean, progressive video ### Model Overview **Starlight Sharp** is a diffusion-based video enhancement model optimized for local or cloud processing. It is designed to sharpen low-res blurry videos and improve clarity on small faces. Starlight Sharp is used for restoration, detail recovery and compression cleanup. Unlike Mini, Starlight Sharp assumes a progressive input and does not perform automatic deinterlacing. ### Key Capabilities * Local first diffusion-based restoration optimized for speed and sharp detail * Restores clarity in degraded or low resolution footage * Best suited for progressive or pre-deinterlaced sources in local desktop workflow ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 26.0417 | 11.9179 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"wonder-1"` **Model-Specific Parameters** * `start_idx` β€” integer, default 0 * `end_idx` β€” decimal, default 1000000.0 * `upscaling_factor` β€” decimal, default 1.0 * `low_sharpness` β€” boolean, default `false` * `keep_original` β€” boolean, default `false` * `ffmpeg_encoding` β€” string, optional * `wm_path` β€” string, optional * `ffmpeg_preproc_filters` β€” string, default `""` ### Examples
Cover image
Click to view/files/BWiJ0nROLN3BwpqEBMKUhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F0002.MP4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F0002_1_sls.mp4&src2label=After&zoom=1
Click to view/files/5Aolw92pIhZuz5dow2mzhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_FamilyTrip_2006_01_1_ddv3_2.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FEPRIII_FamilyTrip_2006_01_1_ddv3_2_sls.mp4&src2label=After&zoom=1
# Starlight Fast 1 (Deprecated) First generation generative upscaling for speed ### Model Overview **Starlight Fast 1** is the first generation diffusion video enhancement model optimized for speed. It delivers fast results and is intended for workflows where performance and turnaround time are prioritized over maximum quality. Fast 1 provides automatic enhancement with sharper detail than traditional upscalers, making it well suited for rapid iteration or time sensitive processing that still require stunning results. ### Key Capabilities * First generation fast diffusion model optimized for quick results * Prioritizes speed over maximum quality and realism ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 52.0833 | 23.8357 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slf-1"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 9000 * `video_profile` β€” string, optional * `video_bit_depth` β€” integer, optional * `video_codec` β€” string, optional ### Examples
Cover image
Click to view/files/TVrG25BOq0Pc2N6ZYVcOhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FUnderwater-dreamscape-a-pearl-white-freshwater-angel-fish-g___.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FUnderwater-dreamscape-a-pearl-white-freshwater-angel-fish-g____Precise_Starlight_Speed.mp4&src2label=After&zoom=1
Click to view/files/5dZjn4l9T0haq1WqpJ6hhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAnime%20before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAnime%20After.mp4&src2label=After&zoom=1
# Starlight Fast 2 2x faster diffusion upscaling with higher fidelity ### Model Overview **Starlight Fast 2** is a second generation diffusion-based video enhancement model designed for improved speed and quality. It delivers significantly faster results than Fast 1 while producing more realistic outputs and sharper details. Fast 2 balances performance and quality, making it well suited for high volume processing, rapid turnaround workflows, and scenarios where speed is critical but visual fidelity still matters. ### Key Capabilities * Up to 2Γ— faster performance compared to Starlight Fast 1 * Produces more realistic results and sharper detail than previous model * Ideal for high volume and time sensitive workflows that require speed with improved quality ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 52.0833 | 23.8357 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slf-2"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 9000 * `start_idx` β€” integer, default 0 * `end_idx` β€” decimal, default 1000000.0 * `upscaling_factor` β€” decimal, default 1.0 * `low_sharpness` β€” boolean, default false * `keep_original` β€” boolean, default false * `ffmpeg_encoding` β€” string, optional * `wm_path` β€” string, optional * `ffmpeg_preproc_filters` β€” string, default `""` ### Examples
Cover image
Click to view/files/eP7nHtzTtTTxOPIwXvp5https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FWorldsFair0001-before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FWorldsFair0001-before_Precise_Starlight_Fast_2.mp4&src2label=After&zoom=1
Click to view/files/YdT7t4lIkuQwR8KAKvV5https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6429487_Woodpecker%20Bird%20Autumn%20Telephoto_By_Edwin_Haighton_Artlist_4K.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6429487_Woodpecker%20Bird%20Autumn%20Telephoto_By_Edwin_Haighton_Artlist_4K_slf.mp4&src2label=Starlight%20Fast%202&zoom=1
# Astra Creative Video Upscale & Enhancement ### Model Family Overview Creative video enhancement models for upscaling GenAI video to 4K while generating new and dynamic details. {% hint style="info" %} Creative models add new levels of detail that can change objects, identity, and stylization. {% endhint %} ### Key Features **Creative diffusion-based upscaling for GenAI video** * Enhance AI-generated footage using generative models designed for expressive, stylized results. **Transform video with new detail and new texture** * Add clarity, richness, and visual complexity while maintaining the character of the original generation. **Adjustable creative intensity** * Control the level of transformation, from subtle enhancement to bold, stylized creative detail. **Cloud-optimized large model.** * A resource intensive model available exclusively through cloud processing. ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | \~7.7 | 4.3 | {% hint style="info" %} For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Models
Cover image
Astra Creative/files/KYbAtzB6ju9LGyJN1Ucr/pages/Mve82EJZCOmYVbnL9p4k
# Astra 1 (Deprecated) Transform GenAI video to 4K with creative upscaling that generates dynamic new texture and detail ### Model Overview **Astra** **1** is a creative diffusion-based upscaling model designed specifically for GenAI video. It transforms AI-generated footage to 4K by adding new, dynamic detail and texture, producing expressive and stylized results beyond traditional enhancement. Astra 1 allows creators to control the level of creative transformation, from subtle refinement to bold, highly stylized output. It enhances clarity, richness, and visual complexity by adding new detail and texture to GenAI video. Due to its scale and creative flexibility, Astra 1 is a cloud-only model optimized for high-capacity processing. ### Key Capabilities * Creative diffusion-based upscaling for GenAI video at 4K * Adds new detail and texture with adjustable creative intensity * Cloud-optimized model for expressive, stylized enhancement workflows ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 7.6786 | 4.3 | ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"slc-1"` **Model-Specific Parameters** * `input_frame_count` β€” integer, optional; maximum 450 * `creativity` β€” string (`"low"` | `"middle"` | `"high"`), required * `video_profile` β€” string, optional * `video_bit_depth` β€” integer, optional * `video_codec` β€” string, optional ### Examples
Cover image
Click to view/files/KYbAtzB6ju9LGyJN1Ucrhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAnimated_Dude_Before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FAnimated_Dude_Before_Creative_Starlight_Creative_Bold.mp4&src2label=After&zoom=1
# Astra 2 Enhanced creative upscaling for GenAI video with advanced control over detail and style ### Model Overview **Astra 2** is an advancement in creative diffusion-based upscaling for GenAI video, building on Astra 1 with expanded control over detail generation and stylization. It transforms AI-generated footage by adding new, dynamic detail and texture, with adjustable creativity and sharpness controls and prompt-based guidance for more precise creative direction. Astra 2 performs best on stylized and GenAI sources, as well as wide shots and large-scale scenes where additional detail can be creatively inferred. It enhances clarity, richness, and visual complexity, and is optimized for expressive, stylized workflows. ### Key Capabilities * Creatively transform GenAI sources with new detail and textures * Expanded control with adjustable creativity and sharpness levels, plus prompt-based guidance * Strong performance on stylized content, wide shots, and detail-sparse scenes ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 10 | 6 | ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"ast-2"` **Model-Specific Parameters** * `creativity` β€” decimal from 0.0 to 1.0, required * `prompt` β€” string, optional * `input_frame_count` β€” integer, optional; maximum 9000 *without* prompt | 450 *with* prompt * `input_frame_rate` β€” integer * `input_height` β€” integer * `input_width` β€” integer * `output_height` β€” integer * `output_width` β€” integer * `realism` β€” decimal from 0.0 to 1.0, optional * `sharp` β€” decimal from 0.0 to 1.0, optional, default 0.5 * Pre-enhance sharpness (0.0: Gaussian blur, 0.5: passthrough, 1.0: USM sharpening) ### Examples
Cover image
Click to view/files/ZA7fCILFSifSNUTO8i2Rhttps://compare.topazlabs.com/share/video?src1=https://downloads.topazlabs.com/web-assets/model-examples/video_12.mp4&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/video_12_ast2_C4_S3.mp4&src2label=After&zoom=1.0
Click to view/files/pvbzlmg4fPTQWf4ZID6khttps://compare.topazlabs.com/share/video?src1=https://downloads.topazlabs.com/web-assets/model-examples/video_15.mp4&src1label=Before&src2=https://downloads.topazlabs.com/web-assets/model-examples/video_15_ast2_C4_S3.mp4&src2label=After&zoom=1.0
Click to view/files/cWOxhqdMzMR4vVjftyhkhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo_18.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo_18_ast2_C4_S3.mp4&src2label=After&zoom=1.0
# Denoise Remove Noise and Reduce Grain ### Model Family Overview Specialized denoise models designed for high-resolution footage and challenging low-light conditions. ### Key Features **High fidelity denoising with speed or quality options** * Choose models optimized for faster processing or maximum noise reduction accuracy. **Reduce low-light and sensor noise without smearing detail** * Clean pixel noise and grain introduced by camera sensors while preserving image integrity. **Dedicated noise reduction for advanced workflows** * Use Nyx High Fidelity to export noise pass for compositing or further refinement. ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above pricing is for our "Quality" models. "Fast" models are priced at roughly 50% of the "Quality" models for common output resolutions and durations. Note: `Nyx` is priced in terms of frames per credit, unlike the other models in this family, so pricing for model will be slightly different than the pricing table above.\ \ For more accurate estimates we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit/calculator). {% endhint %} ### Models #### "Quality" Models
Cover image
Nyx/files/ptKERNpLOJQvXRdDVsls/pages/7k4sYbZxetGwBC7ITaWQ
Nyx High Fidelity/files/vziq4Wm0JIgJVbBGIcGV/pages/6YF8cnnUsVxCJzlpOelI
Nyx XL/files/R7rJlYdeaCfgWKB9JNqF/pages/C3XrFvR3gc9CAUBRknnK
#### "Fast" Models
Cover image
Nyx Fast/files/48QcUSkjNeGRi7iOYXcD/pages/Pe9a9zZBnPDMOY4weOn7
# Nyx High-quality denoising with natural texture preservation ### Model Overview **Nyx** is a high-quality video denoising model designed to reduce noise and grain while preserving fine detail and natural texture. It is optimized for camera-based footage, especially content affected by sensor noise, low-light conditions, or heavy compression. Nyx focuses exclusively on noise reduction without sharpening or creative modification, making it ideal for clean preprocessing or standalone denoising workflows. ### Key Capabilities * High-quality denoising with natural texture preservation * Reduces sensor noise and grain without smearing detail * Dedicated noise reduction without added enhancement ### Pricing | Frames Per Credit β€” 1080p | Frames Per Credit β€” 4k | | ------------------------- | ---------------------- | | 518 | 129 | ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"nyx-3"` **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to viewhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fred-before.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRed-Nyx-after.mp4&src2label=After&zoom=1/files/ptKERNpLOJQvXRdDVsls
# Nyx High Fidelity Precision denoising with pipeline-ready outputs ### Model Overview **Nyx High Fidelity** is a denoise-only model designed to remove grain and noise from high resolution sources while preserving the original image exactly as captured. It performs no sharpening, enhancement, or creative modification, making it ideal for workflows where source fidelity must remain untouched. Nyx High Fidelity supports advanced finishing pipelines by generating noise passes for external compositing, allowing teams to reintroduce grain or manage noise downstream with full control. ### Key Capabilities * Maximum detail preservation during noise reduction * Supports noise pass export for advanced compositing workflows * Ideal for high-end post-production and finishing pipelines ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video]() * `model` β€” `"nxhf-1"` **Model-Specific Parameters** * No parameters {% hint style="info" %} Nyx High Fidelity Denoise is designed to be a dedicated denoise model and **does not support the ability to upscale**. {% endhint %} ### Examples
Cover image
Click to view/files/vziq4Wm0JIgJVbBGIcGVhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcar_guy_short.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fcar_guy_short_1_denoise.mp4&src2label=After&zoom=1
Click to view/files/mFXxiAXq9VfmgvWVwMOHhttps://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6553847_Eating-Fish-Faroe-Islands-Puffin_By_Nathan_Moine_Artlist_4K_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6553847_Eating-Fish-Faroe-Islands-Puffin_By_Nathan_Moine_Artlist_4K_tvai_denoise.mp4&src2label=After&zoom=1
# Nyx XL High-intensity denoising for extreme noise ### Model Overview **Nyx XL** is an intensity-focused denoising model designed for aggressive noise and grain reduction. It applies stronger noise suppression than standard Nyx, making it suitable for severely noisy footage and difficult capture conditions. Nyx XL should be used selectively, as its aggressive denoising prioritizes noise removal over maximum texture retention. ### Key Capabilities * High-intensity denoising for extremely noisy footage * Strong grain and noise suppression in difficult conditions * Best used selectively for challenging sources ### Pricing | Duration | 720p | 1080p | 4K | | -------- | ---- | ----- | --- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 3 | | **10s** | 1 | 2 | 6 | | **1m** | 4 | 8 | 31 | | **5m** | 17 | 38 | 151 | | **10m** | 34 | 76 | 302 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator). {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"nxl-1"` **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view/files/R7rJlYdeaCfgWKB9JNqFhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F694952_Makeup-Nightclub-Lipstick-Looking_By_Omri_Ohana_Artlist_HD.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F694952_Makeup-Nightclub-Lipstick-Looking_By_Omri_Ohana_Artlist_HD_4K_nxl1.mp4&src2label=After&zoom=1
# Nyx Fast Fast denoising for high-volume workflows ### Model Overview **Nyx Fast** is a performance-optimized variant of Nyx designed for faster denoising with reduced computational cost. It provides effective noise reduction for workflows where speed and turnaround time are prioritized. Nyx Fast is well suited for previews, batch processing, and time-sensitive workflows where clean results are needed quickly. ### Key Capabilities * Faster denoising optimized for speed and efficiency * Effective noise reduction for high-volume workflows * Ideal for rapid turnaround and preview processing ### Pricing | Duration | 720p β†’ 720p | 1080p β†’ 1080p | 4K β†’ 4K | | -------- | ----------- | ------------- | ------- | | **1s** | 1 | 1 | 1 | | **5s** | 1 | 1 | 2 | | **10s** | 1 | 1 | 3 | | **1m** | 2 | 4 | 16 | | **5m** | 9 | 19 | 76 | | **10m** | 17 | 38 | 151 | {% hint style="info" %} The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our [Credit Calculator](https://developer.topazlabs.com/credit-calculator).\ \ Additonally, `nxf-1` is a 1x only model, so it cannot upscale video resolution. {% endhint %} ### Getting Started **Endpoint** * [https://api.topazlabs.com/video/]() * `model` β€” `"nxf-1"` **Model-Specific Parameters** * `video_type` β€” `"Progressive"`, `"Interlaced"`, or `"ProgressiveInterlaced"` * `auto` β€” `"Auto"`, `"Manual"`, or `"Relative"` * `field_order` β€” `"TopFirst"`, `"BottomFirst"`, or `"Auto"` * `focus_fix_level` β€” `"None"`, `"Normal"`, or `"Strong"` * `compression` β€” decimal between -1 and 1 * `details` β€” decimal between -1 and 1 * `prenoise` β€” decimal between 0 and 0.1 * `noise` β€” decimal between -1 and 1 * `halo` β€” decimal between -1 and 1 * `preblur` β€” decimal between -1 and 1 * `blur` β€” decimal between -1 and 1 * `grain` β€” decimal between 0 and 0.1 * `grain_sigma` β€” decimal between 0 and 1 * `grain_size` β€” decimal between 0 and 5 * `grain_type` β€” `"silver_rich"`, `"gaussian"`, or `"grey"` * `recover_original_detail_value` β€” decimal between 0 and 1 ### Examples
Cover image
Click to view/files/48QcUSkjNeGRi7iOYXcDhttps://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6309552_Raver-Man-Fire-Twirling-Torch_By_Justinography_Artlist_4K_short_tvai.mp4&src1label=Before&src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2F6309552_Raver-Man-Fire-Twirling-Torch_By_Justinography_Artlist_4K_short_nxf1.mp4&src2label=After&zoom=1
--- [Next Page](/llms-full.txt/1)