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
|
A person walking confidently down a busy street
|
Text description of the video. Be detailed about the person, actions, and scene.
|
| reference_image |
string
|
Reference image to control the person's appearance (optional)
|
|
| audio |
string
|
Audio file for lip-sync and movement synchronization (optional)
|
|
| width |
integer
|
1280
Min: 640 Max: 1344 |
Video width in pixels (will be rounded to nearest multiple of 8)
|
| height |
integer
|
720
Min: 384 Max: 768 |
Video height in pixels (will be rounded to nearest multiple of 8)
|
| num_frames |
integer
|
49
Min: 1 Max: 97 |
Number of frames (25 fps, so 25 frames = 1 second)
|
| num_inference_steps |
integer
|
20
Min: 5 Max: 100 |
Denoising steps. More steps = higher quality but slower
|
| guidance_scale |
number
|
4
Min: 1 Max: 20 |
Text guidance strength. Higher = follows prompt more closely. Lower values (3-5) often produce more natural lighting.
|
| audio_guidance_scale |
number
|
5.5
Min: 1 Max: 20 |
Audio guidance strength (when audio provided). Higher = better sync
|
| seed |
integer
|
Max: 2147483647 |
Random seed for reproducible generation
|
| negative_prompt |
string
|
blurry, low quality, distorted, bad anatomy
|
What to avoid in the video
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}