GET

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

Accept:

kind inputactivity videohash 1bdb7cf7…extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

11 properties · 2 required · 2 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the video from.
video_url*	string	The video to generate the video from.
loras	LoraWeight[]	The LoRAs to use for the image generation. We currently support one lora.	default: []
strength	number	The strength to use for Video to Video. 1.0 completely remakes the video while 0.0 preserves the original.	0.05 ≤ n ≤ 1 · default: 0.8
negative_prompt	string	The negative prompt to generate video from	default: ""
export_fps	integer	The target FPS of the video	4 ≤ n ≤ 32 · default: 16
seed	integer	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_steps	integer	The number of inference steps to perform.	1 ≤ n ≤ 50 · default: 50
use_rife	boolean	Use RIFE for video interpolation	default: true
guidance_scale	number	The 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_size	ImageSize \| enum	The 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/video-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}