You're looking at a specific version of this model. Jump to the model overview.
fmxexpress /flux-lora-training:3eab04e6
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 |
|---|---|---|---|
| images |
string
|
A zip/tar file containing the images that will be used for training. File names must be their captions: a_photo_of_TOK.png, etc. Min 12 images required.
|
|
| model_name |
string
|
black-forest-labs/FLUX.1-dev
|
Model name
|
| hf_token |
string
|
HuggingFace token to use for accessing model
|
|
| steps |
integer
|
1000
Min: 10 Max: 4000 |
Number of training steps. Recommended range 500-4000
|
| learning_rate |
number
|
0.0004
|
Learning rate
|
| batch_size |
integer
|
1
|
Batch size
|
| resolution |
string
|
512,768,1024
|
Image resolutions for training
|
| lora_linear |
integer
|
16
|
LoRA linear value
|
| lora_linear_alpha |
integer
|
16
|
LoRA linear alpha value
|
| repo_id |
string
|
Enter HuggingFace repo id to upload LoRA to HF. Will return zip file if left empty.Ex: lucataco/flux-dev-lora
|
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'}