GET

/v1/schemas/fal/video/fal-ai/ltx-video-v095/multiconditioning

Accept:

kind inputactivity videohash 34bc25d4…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `c8e0321e35ba0771e349f25dd3ccc152c219ebc5df365c864f670825602f332d` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

10 properties · 1 required · 2 $defs

property	type	description	constraints
prompt*	string	Text prompt to guide generation
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
aspect_ratio	enum	Aspect ratio of the generated video (16:9 or 9:16).	9:16 \| 16:9 · default: "16:9"
videos	VideoConditioningInput[]	Videos to use as conditioning	default: []
negative_prompt	string	Negative prompt for generation	default: "worst quality, inconsistent mot…
seed	integer	Random seed for generation	nullable
resolution	enum	Resolution of the generated video (480p or 720p).	480p \| 720p · default: "720p"
num_inference_steps	integer	Number of inference steps	2 ≤ n ≤ 50 · default: 40
expand_prompt	boolean	Whether to expand the prompt using the model's own capabilities.	default: true
images	ImageConditioningInput[]	URL of images to use as conditioning	default: []

Types

2 $defs

ImageConditioningInputobject

image_url*	string	URL of image to use as conditioning
start_frame_num*	integer	Frame number of the image from which the conditioning starts. Must be a multiple of 8.	0 ≤ n ≤ 120

VideoConditioningInputobject

video_url*	string	URL of video to be extended
start_frame_num*	integer	Frame number of the video from which the conditioning starts. Must be a multiple of 8.	0 ≤ n ≤ 120

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-video-v095/multiconditioning","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}