You're looking at a specific version of this model. Jump to the model overview.
venislathiya814092 /omniavatar29:2a5becba
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 |
|---|---|---|---|
| image |
string
|
Reference face/portrait image.
|
|
| audio |
string
|
Driving audio clip (wav/mp3). Output length matches this audio's duration.
|
|
| prompt |
string
|
A person is talking.
|
Text prompt describing the desired scene/motion (e.g. 'A person is talking passionately').
|
| num_steps |
integer
|
50
Min: 1 Max: 100 |
Diffusion denoising steps per chunk. Lower = faster, lower quality.
|
| guidance_scale |
number
|
4.5
Min: 1 Max: 15 |
Classifier-free guidance scale.
|
| audio_scale |
number
|
0
Max: 15 |
Audio guidance scale. Defaults to guidance_scale when left at 0.
|
| tea_cache_l1_thresh |
number
|
0
Max: 1 |
TeaCache step-skipping threshold (0 disables; e.g. 0.05-0.15 speeds up generation at some quality cost).
|
| seed |
integer
|
42
|
Random seed.
|
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'}