cjwbw / dreambooth-avatar

Dreambooth finetuning of Stable Diffusion (v1.5.1) on Avatar art style by Lambda Labs

  • Public
  • 585 runs
  • T4
Iterate in playground

Input

string
Shift + Return to add a new line

Input prompt

Default: ""

string
Shift + Return to add a new line

Specify things to not see in the output

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

integer
(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

string

Choose a scheduler.

Default: "DPMSolverMultistep"

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in

Run time and cost

This model costs approximately $0.035 to run on Replicate, or 28 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 3 minutes. The predict time for this model varies significantly based on the inputs.

Readme

weights: https://huggingface.co/lambdalabs/dreambooth-avatar

Dreambooth style: Avatar

Dreambooth finetuning of Stable Diffusion (v1.5.1) on Avatar art style by Lambda Labs.

About

This text-to-image stable diffusion model was trained with dreambooth.
Put in a text prompt and generate your own Avatar style image!

pk1.jpg

Model description

Base model is Stable Diffusion v1.5 and was trained using Dreambooth with 60 input images sized 512x512 displaying Avatar character images. The model is learning to associate Avatar images with the style tokenized as ‘avatarart style’. Prior preservation was used during training using the class ‘Person’ to avoid training bleeding into the representations for that class. Training ran on 2xA6000 GPUs on Lambda GPU Cloud for 700 steps, batch size 4 (a couple hours, at a cost of about $4).

Author: Eole Cervenka