You're looking at a specific version of this model. Jump to the model overview.
lucataco /train-text-to-image-lora:aa769732
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 |
|---|---|---|---|
| base_model |
string
|
runwayml/stable-diffusion-v1-5
|
Base huggingface model to use
|
| dataset |
string
|
lambdalabs/naruto-blip-captions
|
Huggingface dataset to use
|
| dataloader_num_workers |
integer
|
8
Min: 1 Max: 16 |
Number of workers for dataloader
|
| resolution |
integer
|
512
Min: 128 Max: 1024 |
Resolution for training
|
| train_batch_size |
integer
|
1
Min: 1 Max: 4 |
Batch size for training
|
| num_train_epochs |
integer
|
100
Min: 1 Max: 10000 |
Number of training epochs
|
| gradient_accumulation_steps |
integer
|
4
Min: 1 Max: 8 |
Gradient accumulation steps
|
| max_train_steps |
integer
|
1000
Min: 1 Max: 100000 |
Maximum number of training steps
|
| learning_rate |
number
|
0.0001
Min: 0.0001 Max: 0.01 |
Learning rate for training
|
| max_grad_norm |
number
|
1
Min: 0.1 Max: 10 |
Maximum gradient norm
|
| lr_scheduler |
None
|
cosine
|
Learning rate scheduler
|
| validation_prompt |
string
|
A naruto with blue eyes.
|
Validation prompt
|
| seed |
integer
|
Seed for reproducibility
|
|
| hf_token |
string
|
Huggingface token
|
|
| hub_model_id |
string
|
naruto-lora
|
Huggingface model id to upload to
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}