Skip to main content
Video upscaling lets you enhance existing videos to higher resolutions while improving visual quality. The Topaz Video Upscale model uses AI-powered upscaling to increase resolution by 2x or 4x, or apply quality enhancement at the original resolution (1x).

How it works

Video upscaling uses the same async queue system as video generation:
  1. Queue — Submit your video to /video/queue with the topaz-video-upscale model
  2. Poll — Call /video/retrieve with model and the returned queue_id. While the job runs, it returns JSON with "status": "PROCESSING". When the job finishes, the response body is the upscaled MP4 (Content-Type: video/mp4), so save it to a file. There is no output URL.
  3. Clean up (optional) — After you’ve saved the file, call /video/complete to delete the stored output
The server automatically detects the input video’s duration, frame rate, and dimensions from the uploaded file. You don’t need to provide these values — billing is calculated from the actual video metadata.

Upscale factors

The upscale_factor parameter replaces resolution for upscale models. Passing resolution will return an error. This is because the output resolution depends on the input video’s dimensions — a 2x upscale of a 720p video produces a different result than a 2x upscale of a 480p video.

Supported input formats

  • Formats: MP4, MOV, WebM
  • Input methods: HTTPS URL or data:video/...;base64,... data URL
  • Max duration: 300 seconds (5 minutes)

API usage

Queue an upscale job

The response includes a queue_id to track the job:

Poll and save the result

The finished upscale is the response body itself, not a JSON field, so check Content-Type before parsing. The cURL example prints the content type of each response: repeat it until it prints video/mp4, at which point upscaled.mp4 holds the video. If the queue response included a download_url, retrieve returns JSON with "status": "COMPLETED" instead, and you download the file from that URL. See Private download links.

Clean up (optional)

After you’ve saved the MP4, you can call /video/complete to delete the stored output. It doesn’t return the video or a URL.

API parameters

Parameters not used for upscale models

The following parameters are not accepted for topaz-video-upscale and will return an error if provided: The duration parameter is also ignored — the server detects duration directly from the video file for billing accuracy.

Pricing

Pricing is based on duration, output resolution tier, and frame rate. The output resolution tier is determined by the input video’s height multiplied by the upscale factor.

Output resolution tiers

Videos with frame rates above 48fps cost 2x the per-second rate.

Pricing examples

Use the Video Quote API to get exact pricing before submitting a job.

Getting a quote

video_url is required for quotes on upscale models — the quote endpoint fetches the file and detects duration, FPS, and height from the bytes, so there is no need to supply them. Omitting it returns 400 with “video_url is required for quotes on this model”. Quotes for upscale models require an API key. Requests without one return 403. Pass the same upscale_factor (1, 2, or 4) to /video/quote that you will send to /video/queue, so the quote matches the job. Quote also accepts resolution ("2x" or "4x") as a deprecated alias for upscale models; if both are sent, upscale_factor takes precedence.

Troubleshooting