lightricks/ltx-2-distilled

LTX-2: The first open source audio-video model

Capabilities

Reference Images Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt` *	string	Text prompt for video generation.	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video. Ignored if an image is provided.	`"16:9"`	16:9 9:16 4:3 3:4 1:1 21:9
`enhance_prompt`	boolean	Use the model's prompt enhancement to expand and improve your prompt.	`false`	—
`image`	string (uri)	Optional input image for image-to-video generation.	`—`	—
`image_strength`	number	Strength of image conditioning for i2v (0.0-1.0). Higher values follow the image more closely.	`1`	min: 0, max: 1
`num_frames`	integer	Number of frames to generate. Must follow formula: 8*k + 1 (e.g., 81, 97, 113, 121).	`121`	min: 25, max: 241
`seed`	integer	Random seed for reproducibility.	`—`	—

prompt required string

Text prompt for video generation.

aspect_ratio string

Aspect ratio of the generated video. Ignored if an image is provided.

Default: "16:9"

16:9 9:16 4:3 3:4 1:1 21:9

enhance_prompt boolean

Use the model's prompt enhancement to expand and improve your prompt.

Default: false

image string

Optional input image for image-to-video generation.

image_strength number

Strength of image conditioning for i2v (0.0-1.0). Higher values follow the image more closely.

Default: 1 min: 0, max: 1

num_frames integer

Number of frames to generate. Must follow formula: 8*k + 1 (e.g., 81, 97, 113, 121).

Default: 121 min: 25, max: 241

seed integer

Random seed for reproducibility.

Version: 6707072d3b2a Updated: 6/26/2026 23.8K runs