You're looking at a specific version of this model. Jump to the model overview.
lucataco /musubi-tuner:6a6dbed2
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 |
|---|---|---|---|
| input_videos |
string
|
ZIP file containing video dataset & captions
|
|
| epochs |
integer
|
16
Min: 10 Max: 1000 |
Number of training steps
|
| rank |
integer
|
32
Min: 8 Max: 128 |
LoRA rank
|
| batch_size |
integer
|
4
Min: 1 Max: 4 |
Batch size
|
| learning_rate |
number
|
0.001
Min: 0.00001 Max: 1 |
Learning rate
|
| optimizer |
string
(enum)
|
adamw8bit
Options: adamw, adamw8bit, AdaFactor, adamw16bit |
Optimizer type
|
| seed |
integer
|
42
|
Random seed
|
| hub_model_id |
string
|
|
Hugging Face model path to upload trained LoRA
|
| hf_token |
string
|
|
Hugging Face token for model upload
|
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'}