You're looking at a specific version of this model. Jump to the model overview.
lucataco /ltx-video-0.9.8-distilled:6757cbce
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Text prompt for video generation
|
|
| image |
string
|
Input image for image-to-video generation. If provided, will generate video from this image.
|
|
| video |
string
|
Input video for video-to-video generation. If provided, will generate video from this video. Takes precedence over image if both are provided.
|
|
| negative_prompt |
string
|
worst quality, inconsistent motion, blurry, jittery, distorted
|
Negative prompt for video generation.
|
| resolution |
integer
(enum)
|
720
Options: 480, 720 |
Resolution for the output video (height in pixels).
|
| aspect_ratio |
string
(enum)
|
match_input_image
Options: 16:9, 1:1, 9:16, match_input_image |
Aspect ratio for the output video.
|
| num_frames |
integer
|
121
Min: 9 Max: 257 |
Number of frames per segment. Use 257 for ~10.7s segments at 24fps (recommended for long videos).
|
| num_inference_steps |
integer
|
24
Min: 2 Max: 50 |
Number of denoising steps for initial generation.
|
| guidance_scale |
number
|
3
Min: 1 Max: 10 |
Guidance scale. Recommended range: 3.0-3.5.
|
| fps |
integer
|
24
Min: 1 Max: 60 |
Frames per second for the output video.
|
| seed |
integer
|
Random seed for reproducible results. Leave blank for a random seed.
|
|
| downscale_factor |
number
|
0.667
Min: 0.1 Max: 1 |
Factor to downscale initial generation (recommended: 2/3 for better quality).
|
| denoise_strength |
number
|
0.4
Max: 1 |
Denoising strength for final refinement step.
|
| final_inference_steps |
integer
|
10
Min: 1 Max: 50 |
Number of inference steps for final denoising.
|
| conditioning_frames |
integer
|
21
Min: 1 Max: 50 |
Number of frames to use for video-to-video conditioning (only used when video input is provided).
|
| go_fast |
boolean
|
True
|
Enable fast mode with skip layer strategies (20-40% faster but slightly lower quality).
|
| max_duration_seconds |
integer
|
5
Min: 5 Max: 60 |
Target video duration in seconds. Videos longer than 10s use autoregressive generation.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}