Waifu-Diffusers / README.md
multimodalart's picture
Update README.md
320c67c
|
raw
history blame
644 Bytes
metadata
language:
  - en
tags:
  - stable-diffusion
  - text-to-image
license: unknown
datasets:
  - Danbooru2021
inference: true

Repo Overview

A version of Waifu Diffusion v1.3 with half precision 16 float number and VAE from Waifu Diffusers v1.4 converted to work with Diffusers library.

Model Description

The current model has been fine-tuned with a learning rate of 5.0e-6 for 10 epochs on 680k anime-styled images.

Global Step: 683410

Source

Original model by hakurei: https://huggingface.co/hakurei/waifu-diffusion-v1-3

Original VAE: https://huggingface.co/hakurei/waifu-diffusion-v1-4