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 dancing to energetic music
|
Text description of the desired video
|
| image |
string
|
Optional reference image for character/scene (for text+image or text+image+audio modes)
|
|
| audio |
string
|
Optional audio file for synchronization (for text+audio or text+image+audio modes)
|
|
| mode |
None
|
text_only
|
Generation mode based on available inputs
|
| frames |
integer
|
97
Min: 1 Max: 97 |
Number of frames to generate (HuMo is trained on 97-frame sequences)
|
| height |
None
|
720
|
Video height in pixels
|
| width |
None
|
1280
|
Video width in pixels (recommended: 832 for 480p, 1280 for 720p)
|
| steps |
integer
|
50
Min: 30 Max: 50 |
Number of denoising steps (higher = better quality, slower generation)
|
| scale_t |
number
|
1
Max: 2 |
Text guidance strength (higher = better text adherence)
|
| scale_a |
number
|
1
Max: 2 |
Audio guidance strength (higher = better audio synchronization)
|
| seed |
integer
|
-1
|
Random seed for reproducible results. Use -1 for 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'}