Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Frame Interpolation

Change Frame Rates and Create Smooth Slow Motion

Frame interpolation models change frame rates or create smooth slow motion by generating new frames between existing ones, preserving motion continuity and visual detail.

Models

Choosing a Model

  • Apollo handles non-linear or slightly blurry motion reliably and excels at precise frame multiples (2×, 4×, 8×).

  • Chronos is well suited to linear and layered motion and more challenging frame rate conversions.

  • Aion is built for high-resolution footage with heavy parallax, fast camera movement, or immersive formats, where maximum motion accuracy is required.

  • Apollo Fast and Chronos Fast prioritize speed at about half the cost, for simpler motion, longer sequences, and time-sensitive work.

Best Use Cases

  • Apollo. Structured retiming and slow motion at exact frame multiples.

  • Chronos. Frame rate conversion between common or custom rates without jitter.

  • Aion. Extreme slow motion on complex, high-resolution, motion-heavy footage.

  • Apollo Fast. Quick retiming of simple motion.

  • Chronos Fast. Fast frame rate conversion for long sequences.

Pricing

Frame interpolation models are priced by output frame count, output/input fps ratio, and slow motion factor. For the Chronos models and for requests where there is no slow motion factor (slowmo = 1) and the fps ratio (output fps / input fps) is 2 or less, the credit cost is 1 credit per generated gigapixel. For requests where slow motion factor is greater than 1 or the fps ratio is greater than 2, credit cost is based on the model's multiplier:

Model
Multiplier

Apollo Fast

2

Apollo

4

Aion

8

Each model page lists estimated costs for common slow-motion factors and resolutions. For estimates on your own files, use the Credit Calculator.

Endpoints

Endpoint
Use when

https://api.topazlabs.com/video/

You can supply full source metadata and want a credit estimate before uploading. Follow with PATCH /video/{requestId}/accept and PATCH /video/{requestId}/complete-upload/.

https://api.topazlabs.com/video/express

You only know the container. Returns upload URLs right away, with no accept or complete-upload steps. Note that this endpoint is only available for GAN models (i.e. most creative and generative upscaling models will not be supported).

Every model in this family works on both endpoints. Requests are JSON: put the model's code in a filters object, along with any of its model parameters. Poll GET /video/{requestId}/status and download the result from the URL in the status response.

Parameters

Request parameters are the same for every video model and are listed on the Request Parameters page. output.frameRate is only used when a frame interpolation model is in filters; on /video/express it's required when the filter doesn't set its own fps. Each model's filter parameters (slowmo, fps, duplicate, duplicateThreshold) are listed on its model page.

Limitations

Frame interpolation models don't upscale; output resolution matches the source unless an upscaling model is also in filters.

Helpful Resources

Last updated

Was this helpful?