GET

/v1/schemas/fal/video/fal-ai/cogvideox-5b

Accept:

kind inputactivity videohash 46064467…extracted Oct 24, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `f3b8ef4f6b624b1dc071a51123d6bc77f49a797b86f082fc445cf89074666c18` { "fetchedAt": 1792818001, "extractorVersion": "1", "verifiedAt": null }

Request body

11 properties · 1 required · 2 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the video from.
negative_prompt	string	The negative prompt to generate video from	default: ""
loras	LoraWeight[]	The LoRAs to use for the image generation. We currently support one lora.	default: []
use_rife	boolean	Use RIFE for video interpolation	default: true
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
export_fps	integer	The target FPS of the video	4 ≤ n ≤ 32 · default: 16
video_size	ImageSize \| enum	The size of the generated video.	default: {"width":720,"height":480}
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	default: false
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
num_inference_steps	integer	The number of inference steps to perform.	1 ≤ n ≤ 50 · default: 50
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

Types

2 $defs

ImageSizeobject

width	integer	The width of the generated image.	0 < n ≤ 14142 · default: 512
height	integer	The height of the generated image.	0 < n ≤ 14142 · default: 512

LoraWeightobject

path*	string	URL or the path to the LoRA weights.
scale	number	The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model.	0 ≤ n ≤ 4 · default: 1

Validate a payload

before you spend tokens

shell

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