You're looking at a specific version of this model. Jump to the model overview.
zsxkib /step-video-t2v:beab8fb9
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
|
An astronaut on the Moon discovers a monolith with the text 'STEPFUN' glowing brightly. Ultra HD, HDR video, highly detailed.
|
Descriptive text for what you want to see in the video.
|
| negative_prompt |
string
|
dark, low-resolution, extra hands, watermark, text overlays
|
Negative prompt for undesirable artifacts.
|
| num_inference_steps |
integer
|
30
|
Number of denoising steps.
|
| cfg_scale |
number
|
9
|
Classifier-free guidance scale.
|
| num_frames |
integer
|
51
|
Number of frames in the generated video.
|
| seed |
integer
|
42
|
Seed for reproducibility.
|
| tiled |
boolean
|
False
|
Enable memory-efficient tiled generation
|
| tile_size |
integer
|
34
|
Size of each tile (applies to both height and width)
|
| tile_stride |
integer
|
16
|
Stride between tiles (applies to both directions)
|
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'}