> For the complete documentation index, see [llms.txt](https://developer.topazlabs.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.topazlabs.com/whats-new.md).

# What's New?

Check out our latest release

### **Starlight Fast 3**

<table data-card-size="large" data-view="cards"><thead><tr><th align="center"></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td align="center">Click to view</td><td><a href="https://938351258-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fik4tc42rkpL9SRR51NLK%2Fuploads%2Ffpn2awhh2fJ7MKhuBnD5%2Fvideo19-seedance1.5pro-slf3_slider.jpg?alt=media&amp;token=3435e3dd-9da1-40c1-a40e-f8091f7548f9">video19-seedance1.5pro-slf3_slider.jpg</a></td><td><a href="https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo19-seedance1.5pro-slf3-before.mp4&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo19-seedance1.5pro-slf3-after.mp4&#x26;src2label=After&#x26;zoom=1">https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo19-seedance1.5pro-slf3-before.mp4&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo19-seedance1.5pro-slf3-after.mp4&#x26;src2label=After&#x26;zoom=1</a></td></tr><tr><td align="center">Click to view</td><td><a href="https://938351258-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fik4tc42rkpL9SRR51NLK%2Fuploads%2FqR8SYHySr9CT11rls6Dk%2Fvideo38-veo3.1-slf3_slider.jpg?alt=media&amp;token=ce294f3a-095f-498b-bfbe-68f036a04674">video38-veo3.1-slf3_slider.jpg</a></td><td><a href="https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo38-veo3.1-slf3-before.mp4&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo38-veo3.1-slf3-after.mp4&#x26;src2label=After&#x26;zoom=1">https://compare.topazlabs.com/share/video?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo38-veo3.1-slf3-before.mp4&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Fvideo38-veo3.1-slf3-after.mp4&#x26;src2label=After&#x26;zoom=1</a></td></tr></tbody></table>

{% hint style="success" %}
Visit the [Starlight Fast 3](/video-models/upscaling-and-enhancement/generative/starlight-fast-3.md) page for this model's endpoint, parameters, and more information.
{% endhint %}

**Starlight Fast 3** is the next generation of our Starlight Fast line. It’s a diffusion video enhancement model built for quick iteration and deadline-driven work, for both GenAI and archival footage.

It renders up to **4× faster than Starlight Precise 2.6** with comparable 4K quality. At 1080p output it processes up to 7 frames per second, so a 10-second clip finishes in under 40 seconds. It also uses **scene splitting**, which detects cuts within a clip automatically to keep results stable and consistent across scene changes.

What’s new in Starlight Fast 3:

* Up to 4× faster than Starlight Precise 2.6
* Comparable 4K output quality to Starlight Precise 2.6
* Significantly improved skin, text, and fine detail over Starlight Fast 2
* Scene splitting for better temporal stability at cuts

{% hint style="warning" %}
Starlight Fast 3 replaces Starlight Fast 2, which now falls under our "Legacy" models. For more information and to access Starlight Fast 2, visit our [Model Deprecations](/resources/model-deprecations.md) page.
{% endhint %}

#### How to Choose Between Starlight Models

**Start with Starlight Precise 2.6** (`slp-2.6`) when quality matters most. It's our highest-quality generative video model and produces substantially better results than our faster options. The tradeoff is speed: it runs about 4× slower than Starlight Fast 3.

**Use Starlight Fast 3** (`slf-3`) when you need generative results at volume or on a deadline. It's up to 4× faster than Precise 2.6 and costs the same per frame, with a modest step down in quality.

**Use Starlight Mini** (`slm-1`) for very old, low-quality footage. It's built specifically for degraded archival content, such as early film transfers, VHS, and low-resolution SD, and brings out detail other models can't. Starlight Mini has a slight, inherent softness that suits many archival sources. For the best results on this kind of footage, run Starlight Mini first to restore the source, then run Starlight Precise 2.6 on the result.

{% hint style="info" %}
**Starlight Fast 2** (`slf-2`) is still available at half the price of Starlight Fast 3. Starlight Fast 3 is substantially faster and higher quality, so we recommend it for all new integrations.
{% endhint %}

{% hint style="success" %}
Reference our [Upscaling & Enhancement](/video-models/upscaling-and-enhancement.md) page for more info on our Starlight models.
{% endhint %}

### Keep Learning

Check out some of our other helpful resources.

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-tag">:tag:</i></td><td><h4>Model Pricing</h4></td><td>Learn how we price our models.</td><td><a href="/getting-started/model-pricing.md">Model Pricing</a></td></tr><tr><td><i class="fa-codepen">:codepen:</i></td><td><h4>Model Playground</h4></td><td>Test and create with our models.</td><td><a href="https://playground.topazlabs.com/">https://playground.topazlabs.com/</a></td></tr><tr><td><i class="fa-square-root-variable">:square-root-variable:</i></td><td><h4>Credit Calculator</h4></td><td>Pricing for specific outputs, batches, and more.</td><td><a href="https://developer.topazlabs.com/credit-calculator">https://developer.topazlabs.com/credit-calculator</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://developer.topazlabs.com/whats-new.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.