GET

/v1/schemas/fal/video/fal-ai/ltx-2.3-quality/ingredient

Accept:

kind inputactivity videohash 100c2ca2…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `ffff7fa69c639a15a7cb5514be8e7c42e4a65668b6284b832d6a9512fedda54e` { "fetchedAt": 1783331098, "extractorVersion": "1", "verifiedAt": null }

Request body

16 properties · 2 required · 1 $defs

property	type	description	constraints
prompt*	string	The prompt to guide the generated video. For best results, use a 'Reference sheet: ... Generated video: ...' structure.
image_url*	string	URL of the Ingredient reference sheet image. The sheet should contain clean panels for the characters, props, and location to preserve.
num_frames	integer	The number of frames to generate.	9 ≤ n ≤ 481 · default: 121
enable_prompt_expansion	boolean	Whether to enable prompt expansion.	default: true
frames_per_second	number	Frames per second of the generated video.	1 ≤ n ≤ 60 · default: 24
seed	integer	Random seed for reproducibility. If None, a random seed is chosen.	nullable
ingredient_strength	number	Strength of the built-in Ingredient IC-LoRA. Higher values make the reference sheet identities and props more dominant.	0 ≤ n ≤ 2 · default: 1
enable_safety_checker	boolean	Whether to enable the safety checker.	default: true
sync_mode	boolean	If True, the media is returned as a data URI inline in the response. Useful for short-lived requests and tests.	default: false
guidance_scale	number	Classifier-free guidance scale.	1 ≤ n ≤ 20 · default: 1
video_quality	enum	The quality preset of the generated video.	low \| medium \| high \| maximum · default: "high"
generate_audio	boolean	Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.	default: true
negative_prompt	string	The negative prompt to steer generation away from.	default: "worst quality, inconsistent mot…
resolution	ImageSize \| enum	The final generated video size. The default keeps the workflow's first stage at the Ingredient LoRA's trained 768x448 bucket before the official 2x refinement stage.	default: {"height":896,"width":1536}
reference_strength	number	Strength of the reference-sheet guide. 1.0 uses the sheet fully; lower values give the model more freedom.	0 ≤ n ≤ 2 · default: 1
video_write_mode	enum	The write mode of the generated video.	fast \| balanced \| small · default: "balanced"

Types

1 $defs

ImageSizeobject

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

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-2.3-quality/ingredient","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}