You're looking at a specific version of this model. Jump to the model overview.
genmoai /mochi-1-lora-trainer:9f7c6284
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
|
A zip file containing the video snippets that will be used for training. We recommend a minimum of 12 videos of only a few seconds each. If you include captions, include them as one .txt file per video, e.g. video-1.mp4 should have a caption file named video-1.txt.
|
|
trim_and_crop |
boolean
|
True
|
Automatically trim and crop video inputs
|
steps |
integer
|
100
Min: 10 Max: 6000 |
Number of training steps. Recommended range 500-4000
|
learning_rate |
number
|
0.0004
|
Learning rate, if you're new to training you probably don't need to change this.
|
caption_dropout |
number
|
0.1
Min: 0.01 Max: 1 |
Caption dropout, if you're new to training you probably don't need to change this.
|
batch_size |
integer
|
1
|
Batch size, you can leave this as 1
|
optimizer |
string
|
adamw
|
Optimizer to use for training. Supports: adam, adamw.
|
compile_dit |
boolean
|
False
|
Compile the transformer
|
seed |
integer
|
42
Max: 100000 |
Seed for reproducibility, you can leave this as 42
|
hf_repo_id |
string
|
Hugging Face repository ID, if you'd like to upload the trained LoRA to Hugging Face. For example, lucataco/mochi-lora-vhs. If the given repo does not exist, a new public repo will be created.
|
|
hf_token |
string
|
Hugging Face token, if you'd like to upload the trained LoRA to Hugging Face.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'weights': {'format': 'uri',
'title': 'Weights',
'type': 'string'}},
'required': ['weights'],
'title': 'Output',
'type': 'object'}