falImage to videoComing soon

fal-ai/sadtalker/reference

Name: fal-ai/sadtalker/reference
Brand: fal

fal-ai/sadtalker/reference 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
`source_image_url` required	text	—	URL of the source image
`driven_audio_url` required	text	—	URL of the driven audio
`reference_pose_video_url` required	text	—	URL of the reference video
`pose_style`	number (whole) 0 to 45	0	The style of the pose
`face_model_resolution`	one of 256, 512	256	The resolution of the face model
`expression_scale`	number 0 to 3	1	The scale of the expression
`face_enhancer`	text	—	The type of face enhancer to use
`still_mode`	true or false	false	Whether to use still mode. Fewer head motion, works with preprocess `full`.
`preprocess`	one of crop, extcrop, resize, full, extfull	crop	The type of preprocessing to use

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/sadtalker/reference",
    "input": {
      "source_image_url": "https://storage.googleapis.com/falserverless/model_tests/sadtalker/anime_girl.png",
      "driven_audio_url": "https://storage.googleapis.com/falserverless/model_tests/sadtalker/deyu.wav",
      "reference_pose_video_url": "https://github.com/OpenTalker/SadTalker/raw/main/examples/ref_video/WDA_AlexandriaOcasioCortez_000.mp4"
    }
  }'