learners-superpumped
/
dreambooth-tar
- Public
- 2.5K runs
Run learners-superpumped/dreambooth-tar with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
|---|---|---|---|
| instance_data |
string
|
A ZIP file containing your training images (JPG, PNG, etc. size not restricted). These images contain your 'subject' that you want the trained model to embed in the output domain for later generating customized scenes beyond the training images. For best results, use images without noise or unrelated objects in the background.
|
|
| class_data |
string
|
An optional ZIP file containing the training data of class images. This corresponds to `class_prompt` above, also with the purpose of keeping the model generalizable. By default, the pretrained stable-diffusion model will generate N images (determined by the `num_class_images` you set) based on the `class_prompt` provided. But to save time or to have your preferred specific set of `class_data`, you can also provide them in a ZIP file.
|
|
| resolution |
integer
|
512
|
The resolution for input images. All the images in the train/validation dataset will be resized to this resolution.
|
| ckpt_base |
string
|
https://huggingface.co/BanKaiPls/AsianModel/resolve/main/Brav6.safetensors
|
The base model for tuning
|
| train_batch_size |
integer
|
2
|
Batch size (per device) for the training dataloader.
|
| user_name |
string
|
testuser
|
User name
|
| max_train_steps |
integer
|
1760
|
Total number of training steps to perform. If provided, overrides num_train_epochs.
|
| learning_rate |
number
|
0.00002
|
Initial learning rate (after the potential warmup period) to use.
|
| lr_scheduler |
string
(enum)
|
constant_with_warmup
Options: linear, cosine, cosine_with_restarts, polynomial, constant, constant_with_warmup |
The scheduler type to use
|
| model_id |
string
|
test_model
|
model save path
|
| lr_warmup_steps |
integer
|
176
|
Number of steps for the warmup in the lr scheduler.
|
| lambda_arc |
number
|
0.075
|
Loss weight for arcface loss
|
{
"type": "object",
"title": "Input",
"required": [
"instance_data"
],
"properties": {
"model_id": {
"type": "string",
"title": "Model Id",
"default": "test_model",
"x-order": 9,
"description": "model save path"
},
"ckpt_base": {
"type": "string",
"title": "Ckpt Base",
"default": "https://huggingface.co/BanKaiPls/AsianModel/resolve/main/Brav6.safetensors",
"x-order": 3,
"description": "The base model for tuning"
},
"user_name": {
"type": "string",
"title": "User Name",
"default": "testuser",
"x-order": 5,
"description": "User name"
},
"class_data": {
"type": "string",
"title": "Class Data",
"format": "uri",
"x-order": 1,
"description": "An optional ZIP file containing the training data of class images. This corresponds to `class_prompt` above, also with the purpose of keeping the model generalizable. By default, the pretrained stable-diffusion model will generate N images (determined by the `num_class_images` you set) based on the `class_prompt` provided. But to save time or to have your preferred specific set of `class_data`, you can also provide them in a ZIP file."
},
"lambda_arc": {
"type": "number",
"title": "Lambda Arc",
"default": 0.075,
"x-order": 11,
"description": "Loss weight for arcface loss"
},
"resolution": {
"type": "integer",
"title": "Resolution",
"default": 512,
"x-order": 2,
"description": "The resolution for input images. All the images in the train/validation dataset will be resized to this resolution."
},
"lr_scheduler": {
"enum": [
"linear",
"cosine",
"cosine_with_restarts",
"polynomial",
"constant",
"constant_with_warmup"
],
"type": "string",
"title": "lr_scheduler",
"description": "The scheduler type to use",
"default": "constant_with_warmup",
"x-order": 8
},
"instance_data": {
"type": "string",
"title": "Instance Data",
"format": "uri",
"x-order": 0,
"description": "A ZIP file containing your training images (JPG, PNG, etc. size not restricted). These images contain your 'subject' that you want the trained model to embed in the output domain for later generating customized scenes beyond the training images. For best results, use images without noise or unrelated objects in the background."
},
"learning_rate": {
"type": "number",
"title": "Learning Rate",
"default": 2e-05,
"x-order": 7,
"description": "Initial learning rate (after the potential warmup period) to use."
},
"lr_warmup_steps": {
"type": "integer",
"title": "Lr Warmup Steps",
"default": 176,
"x-order": 10,
"description": "Number of steps for the warmup in the lr scheduler."
},
"max_train_steps": {
"type": "integer",
"title": "Max Train Steps",
"default": 1760,
"x-order": 6,
"description": "Total number of training steps to perform. If provided, overrides num_train_epochs."
},
"train_batch_size": {
"type": "integer",
"title": "Train Batch Size",
"default": 2,
"x-order": 4,
"description": "Batch size (per device) for the training dataloader."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "object",
"title": "TrainingOutput",
"required": [
"weights"
],
"properties": {
"weights": {
"type": "string",
"title": "Weights",
"format": "uri"
}
}
}