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

lucataco /diffusers-dreambooth-lora:fc748962

Input

file

A zip file containing the images that will be used for training.

string
Shift + Return to add a new line

Instance prompt to trigger the image generation

Default: "a photo of TOK dog"

integer

The resolution for input images, all the images in the train/validation dataset will be resized to this

Default: 512

integer
(minimum: 100, maximum: 6000)

Total number of training steps to perform

Default: 500

integer
(minimum: 4, maximum: 64)

The dimension of the LoRA

Default: 4

string

The optimizer type to use

Default: "AdamW"

number
(minimum: 0.0001, maximum: 1)

Initial learning rate to use (1.0 for Prodigy)

Default: 0.0001

Including train_batch_size and 8 more...

Output

No output yet! Press "Submit" to start a prediction.