A .zip or .tar file containing the image files that will be used for fine-tuning

Random seed for reproducible training. Leave empty to use a random seed

Square pixel resolution which your images will be resized to for training

Default: 768

Batch size (per device) for training

Default: 4

Number of epochs to loop through your training dataset

Default: 4000

Number of individual training steps. Takes precedence over num_train_epochs

Default: 1000

Whether to use LoRA training. If set to False, will use Full fine tuning

Default: true

Learning rate for the U-Net. We recommend this value to be somewhere between `1e-6` to `1e-5`.

Default: 0.000001

Scaling of learning rate for training textual inversion embeddings. Don't alter unless you know what you're doing.

Default: 0.0003

Scaling of learning rate for training LoRA embeddings. Don't alter unless you know what you're doing.

Default: 0.0001

Rank of LoRA embeddings. Don't alter unless you know what you're doing.

Default: 32

Learning rate scheduler to use for training

Default: "constant"

Number of warmup steps for lr schedulers with warmups.

Default: 100

A unique string that will be trained to refer to the concept in the input images. Can be anything, but TOK works well

Default: "TOK"

Text which will be used as prefix during automatic captioning. Must contain the `token_string`. For example, if caption text is 'a photo of TOK', automatic captioning will expand to 'a photo of TOK under a bridge', 'a photo of TOK holding a cup', etc.

Default: "a photo of TOK, "

Prompt that describes part of the image that you will find important. For example, if you are fine-tuning your pet, `photo of a dog` will be a good prompt. Prompt-based masking is used to focus the fine-tuning process on the important/salient parts of the image

If you want to crop the image to `target_size` based on the important parts of the image, set this to True. If you want to crop the image based on face detection, set this to False

Default: true

If you want to use face detection instead of CLIPSeg for masking. For face applications, we recommend using this option.

Default: false

How blurry you want the CLIPSeg mask to be. We recommend this value be something between `0.5` to `1.0`. If you want to have more sharp mask (but thus more errorful), you can decrease this value.

Default: 1

verbose output

Default: true

Number of steps between saving checkpoints. Set to very very high number to disable checkpointing, because you don't need one.

Default: 999999

Filetype of the input images. Can be either `zip` or `tar`. By default its `infer`, and it will be inferred from the ext of input file.

Default: "infer"