falVideo to videoComing soon

fal-ai/scail-2

Name: fal-ai/scail-2
Brand: fal

fal-ai/scail-2 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.

Priced by usage

Pricing

$0.13 per second. Measured from the input file. The final charge comes from usage.

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
`prompt` required	text	—	The prompt describing the final video to generate.
`image_url` required	URL or file	—	URL of the reference character image. The character in this image is animated (or used to replace a subject) according to the driving video.
`video_url` required	URL or file	—	URL of the driving (motion) video. The subject can be a human, multiple humans, or an animal.
`mode`	one of animation, replacement	animation	`animation` animates the reference character with the driving motion. `replacement` replaces the driving subject with the reference character while keeping the original scene.
`driving_type`	one of end_to_end, pose	end_to_end	Driving signal for animation mode. `end_to_end` (default) drives directly from the SAM3-masked driving video and is the recommended, most robust path. `pose` renders an explicit NLF/DWPose skeleton from the driving video (more control for challenging inputs).
`subject_type`	one of human, animal	human	Type of subject in the driving video. `animal` switches the SAM3 detection prompt to non-human subjects.
`resolution`	one of 512p, 704p	512p	Output resolution. 512p outputs 896x512 (landscape) or 512x896 (portrait); 704p outputs 1280x704 or 704x1280. Orientation is chosen automatically from the reference image aspect ratio.
`num_inference_steps`	number (whole) 2 to 50	40	Number of diffusion sampling steps. Higher improves quality but is slower.
`guidance_scale`	number 1 to 10	5	Classifier-free guidance scale. Controls prompt adherence versus creativity.
`shift`	number 1 to 10	3	Flow-matching noise schedule shift. 3.0 is recommended for the 512p tier.
`seed`	number (whole)	—	Random seed. Leave empty for a random seed. The seed used is returned in the response.

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/scail-2",
    "input": {
      "prompt": "A person dancing gracefully in a sunlit studio",
      "image_url": "https://v3b.fal.media/files/b/panda/-oMlZo9Yyj_Nzoza_tgds_GmLF86r5bOt50eMMKCszy_eacc949b3933443c9915a83c98fbe85e.png",
      "video_url": "https://v3b.fal.media/files/b/panda/a6SvJg96V8eoglMlYFShU_5385885-hd_1080_1920_25fps.mp4"
    }
  }'