You're looking at a specific version of this model. Jump to the model overview.
alexgenovese /autotrain-dreambooth:c65a88f1
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 |
|---|---|---|---|
| model |
string
|
stabilityai/stable-diffusion-xl-base-1.0
|
HF base model path
|
| prompt |
string
|
a photo of aisudhca bag
|
Instance prompt
|
| train_data_zip |
string
|
Upload image dataset in zip format
|
|
| mixed_precision |
string
(enum)
|
bf16
Options: bf16, fp16 |
FP16 or BF16
|
| train_class_data_zip |
string
|
Upload image dataset in zip format - For Regularization
|
|
| class_prompt |
string
|
Class prompt
|
|
| seed |
integer
|
42
|
Seed
|
| resolution |
integer
(enum)
|
1024
Options: 512, 768, 1024 |
Resolution
|
| center_crop |
boolean
|
False
|
Center crop
|
| train_text_encoder |
boolean
|
True
|
Train text encoder
|
| batch_size |
integer
|
1
|
Train batch size
|
| num_steps |
integer
|
2000
|
Max train steps
|
| checkpointing_steps |
integer
|
500
|
Checkpointing steps
|
| gradient_accumulation |
integer
|
1
|
Gradient accumulation steps
|
| lr |
number
|
0.0004
|
Learning rate
|
| scheduler |
string
(enum)
|
constant
Options: linear, cosine, cosine_with_restarts, polynomial, constant, constant_with_warmup |
Learning rate scheduler
|
| warmup_steps |
integer
|
0
|
Learning rate warmup steps
|
| num_cycles |
integer
|
1
|
Learning rate num cycles
|
| use_8bit_adam |
boolean
|
False
|
Use 8bit adam
|
| xformers |
boolean
|
False
|
Enable xformers memory efficient attention
|
| xl |
boolean
|
True
|
XL
|
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'}