---
language:
- en
tags:
- stable-diffusion
- text-to-image
license: unknown
datasets:
- Danbooru2021
inference: true

---

## Repo Overview

A version of Waifu Diffusion v1.4 Float32 Booru 110k model and VAE from Waifu Diffusion v1.4 converted to work with Diffusers library.

![](https://files.catbox.moe/hqfckc.png)
^ Quality/Style test



![](https://files.catbox.moe/eac57m.png)
^ Unnatural resolution test

![](https://files.catbox.moe/ulrm28.png)
^ Landscape test

![](https://files.catbox.moe/odvq06.png)
^ Extremely long resolution test

## 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

WD v1.4 model: https://huggingface.co/hakurei/waifu-diffusion-v1-4

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