GET

/v1/schemas/fal/video/fal-ai%2Flive-portrait

kind inputactivity videohash 162ef979extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

28 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
video_url*stringURL of the video to drive the lip syncing.
image_url*stringURL of the image to be animated
smilenumberAmount to smile-2 ≤ n ≤ 2 · default: 0
flag_eye_retargetingbooleanWhether to enable eye retargeting.default: false
pupil_ynumberAmount to move pupils vertically-45 ≤ n ≤ 45 · default: 0
scalenumberScaling factor for the face crop.default: 2.3
flag_lip_retargetingbooleanWhether to enable lip retargeting.default: false
rotate_rollnumberAmount to rotate the face in roll-45 ≤ n ≤ 45 · default: 0
blinknumberAmount to blink the eyes-30 ≤ n ≤ 30 · default: 0
woonumberAmount to shape mouth in 'woo' position-100 ≤ n ≤ 100 · default: 0
enable_safety_checkerbooleanWhether to enable the safety checker. If enabled, the model will check if the input image contains a face before processing it. The safety checker will process the input imagedefault: false
flag_do_cropbooleanWhether to crop the source portrait to the face-cropping space.default: true
aaanumberAmount to open mouth in 'aaa' shape-200 ≤ n ≤ 200 · default: 0
flag_relativebooleanWhether to use relative motion.default: true
vx_rationumberHorizontal offset ratio for face crop.default: 0
rotate_yawnumberAmount to rotate the face in yaw-45 ≤ n ≤ 45 · default: 0
pupil_xnumberAmount to move pupils horizontally-45 ≤ n ≤ 45 · default: 0
rotate_pitchnumberAmount to rotate the face in pitch-45 ≤ n ≤ 45 · default: 0
eeenumberAmount to shape mouth in 'eee' position-40 ≤ n ≤ 40 · default: 0
batch_sizeintegerBatch size for the model. The larger the batch size, the faster the model will run, but the more memory it will consume.default: 32
flag_do_rotbooleanWhether to conduct the rotation when flag_do_crop is True.default: true
flag_stitchingbooleanWhether to enable stitching. Recommended to set to True.default: true
eyebrownumberAmount to raise or lower eyebrows-30 ≤ n ≤ 30 · default: 0
flag_lip_zerobooleanWhether to set the lip to closed state before animation. Only takes effect when flag_eye_retargeting and flag_lip_retargeting are False.default: true
winknumberAmount to wink0 ≤ n ≤ 25 · default: 0
flag_pastebackbooleanWhether to paste-back/stitch the animated face cropping from the face-cropping space to the original image space.default: true
dsizeintegerSize of the output image.default: 512
vy_rationumberVertical offset ratio for face crop. Positive values move up, negative values move down.default: -0.125

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/live-portrait","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}