falImage to videoComing soon

fal-ai/vidu/q3/reference-to-video/mix

Name: fal-ai/vidu/q3/reference-to-video/mix
Brand: fal

fal-ai/vidu/q3/reference-to-video/mix 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.

Priced by usage

Pricing

$0.091 per video. The final charge comes from usage.

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 2000 characters
`reference_image_urls` required	URLs or files	—	URLs of 1 to 4 reference images used to keep subjects or scenes consistent
`duration`	number (whole) 1 to 16	5	Duration of the video in seconds (1-16 for Q3 models)
`seed`	number (whole)	—	Random seed for reproducibility. If None, a random seed is chosen.
`aspect_ratio`	one of 16:9, 9:16, 4:3, 3:4, 1:1	16:9	The aspect ratio of the output video
`resolution`	one of 360p, 540p, 720p, 1080p	720p	Output video resolution
`audio`	true or false	true	Whether to use direct audio-video generation. When true, outputs video with sound.

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/vidu/q3/reference-to-video/mix",
    "input": {
      "prompt": "A character walking through a beach catching an apple.",
      "reference_image_urls": [
        "<reference_image_urls>"
      ]
    }
  }'