GET

/v1/schemas/fal/video/fal-ai/ltx-2/image-to-video

Accept:

kind inputactivity videohash 56f1f1c6…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `2ca28bf415a0abdfe9e22eef72a593712772b66fb6c4c143b5080c356742c4c2` { "fetchedAt": 1783329487, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 2 required · 0 $defs

property	type	description	constraints
image_url*	string	URL of the image to generate the video from. Must be publicly accessible or base64 data URI. Supports PNG, JPEG, WebP, AVIF, and HEIF formats.
prompt*	string	The prompt to generate the video from	length ≥ 1 · length ≤ 5000
generate_audio	boolean	Whether to generate audio for the generated video	default: true
fps	enum	The frames per second of the generated video	25 \| 50 · default: 25
resolution	enum	The resolution of the generated video	1080p \| 1440p \| 2160p · default: "1080p"
duration	enum	The duration of the generated video in seconds	6 \| 8 \| 10 · default: 6

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-2/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}