You're looking at a specific version of this model. Jump to the model overview.
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.
|
|
| negative_prompt |
string
|
|
Optional negative prompt. If blank, uses the model default.
|
| resolution |
None
|
832*480
|
Video resolution formatted as width*height.
|
| num_frames |
integer
|
81
Min: 5 Max: 121 |
Desired number of frames (5-121). Internally adjusted to valid 4n+1 values (min 81, max 121).
|
| sample_steps |
integer
|
4
|
Number of diffusion sampling steps.
|
| guidance_scale |
number
|
1
|
Classifier-free guidance scale.
|
| solver |
None
|
unipc
|
Sampling solver.
|
| seed |
integer
|
-1
|
Random seed (-1 for random).
|
| output_format |
None
|
webm
|
Output video format with transparency support.
|
| fps |
integer
|
16
Min: 5 Max: 30 |
Output framerate (5-30 fps).
|
| output_quality |
integer
|
85
Min: 1 Max: 100 |
Output quality (1-100, higher is better).
|
| remove_first_frame |
boolean
|
False
|
Remove the first frame from the final output video.
|
| remove_last_frame |
boolean
|
False
|
Remove the last frame from the final output video.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}