GET

/v1/schemas/fal/video/fal-ai%2Fcogvideox-5b%2Fimage-to-video

kind inputactivity videohash 53ba8784extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

10 properties · 2 required · 2 $defs
propertytypedescriptionconstraints
image_url*stringThe URL to the image to generate the video from.
prompt*stringThe prompt to generate the video from.
lorasLoraWeight[]The LoRAs to use for the image generation. We currently support one lora.default: []
negative_promptstringThe negative prompt to generate video fromdefault: ""
export_fpsintegerThe target FPS of the video4 ≤ n ≤ 32 · default: 16
seedinteger The same seed and the same prompt given to the same version of the model will output the same video every time. nullable
num_inference_stepsintegerThe number of inference steps to perform.1 ≤ n ≤ 50 · default: 50
use_rifebooleanUse RIFE for video interpolationdefault: true
guidance_scalenumberThe CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related video to show you.0 ≤ n ≤ 20 · default: 7
video_sizeImageSize | enumThe size of the generated video.default: {"height":480,"width":720}

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/cogvideox-5b/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}