You're looking at a specific version of this model. Jump to the model overview.

edenartlab /sdxl-lora-trainer:9f6cf388

Playground API

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
checkpoint
string (enum)
sdxl-v1.0

Options:

sdxl-v1.0

Which Stable Diffusion checkpoint to use
lora_training_urls
string
Training images for new LORA concept
instance_prompt
string
a single prompt that describes the concept to be learned
name
string
Name of new LORA concept
resolution
integer
960
Resolution
lr_flip_p
number
0.5
LR flip prob
train_batch_size
integer
2
Batch size
gradient_accumulation_steps
integer
2
Gradient accumulation steps
learning_rate
number
0.00025
Learning rate for U-Net
max_train_steps
integer
500
Max train steps for tuning (U-Net and text encoder)
lora_rank
integer
4
LORA rank

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema 
{'items': {'properties': {'attributes': {'title': 'Attributes',
                                         'type': 'object'},
                          'file': {'format': 'uri',
                                   'title': 'File',
                                   'type': 'string'},
                          'isFinal': {'default': False,
                                      'title': 'Isfinal',
                                      'type': 'boolean'},
                          'name': {'title': 'Name', 'type': 'string'},
                          'progress': {'title': 'Progress', 'type': 'number'},
                          'thumbnail': {'format': 'uri',
                                        'title': 'Thumbnail',
                                        'type': 'string'}},
           'required': ['file'],
           'title': 'CogOutput',
           'type': 'object'},
 'title': 'Output',
 'type': 'array',
 'x-cog-array-type': 'iterator'}