falVideo to videoComing soon

fal-ai/kandinsky6-vsr

Name: fal-ai/kandinsky6-vsr
Brand: fal

fal-ai/kandinsky6-vsr is a video to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`video_url` required	URL or file	—	The input video to upscale. Clips are resampled to 24fps and capped at 121 frames (~5s). For 2x and 4x upscaling, width and height must be multiples of 16.
`upscale_factor`	one of 2, 2.25, 4	2.25	Total upscale factor applied to the input resolution. One of 2, 2.25 or 4.
`num_inference_steps`	number (whole) 2 to 50	5	The number of denoising steps used for each tile.
`seed`	number (whole)	—	The random seed used for the generation process.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/kandinsky6-vsr",
    "input": {
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/seedvr-input.mp4"
    }
  }'