falImage to videoComing soon

fal-ai/framepack

Name: fal-ai/framepack
Brand: fal

fal-ai/framepack is an image 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: 3600s
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	—	Text prompt for video generation (max 500 characters).
`negative_prompt`	text		Negative prompt for video generation.
`image_url` required	URL or file	—	URL of the image input.
`seed`	number (whole)	—	The seed to use for generating the video.
`aspect_ratio`	one of 16:9, 9:16	16:9	The aspect ratio of the video to generate.
`resolution`	one of 720p, 480p	480p	The resolution of the video to generate. 720p generations cost 1.5x more than 480p generations.
`cfg_scale`	number 0 to 7	1	Classifier-Free Guidance scale for the generation.
`guidance_scale`	number 0 to 32	10	Guidance scale for the generation.
`num_frames`	number (whole) 30 to 900	180	The number of frames to generate.

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/framepack",
    "input": {
      "prompt": "A mesmerising video of a deep sea jellyfish moving through an inky-black ocean. The jellyfish glows softly with an amber bioluminescence. The overall scene is…",
      "image_url": "https://storage.googleapis.com/falserverless/framepack/framepack.jpg"
    }
  }'