home models images videos 3D Models articles comics challenges updates shop

Waifu Diffusion

Name: Waifu Diffusion
Rating: 5 (260 reviews)
Author: salt

259

4.4k

Updated: Oct 4, 2024

style

anime

Download

1 variant available

fp16 PickleTensor

wd-v1-3-float32.ckpt

Half precision, best balance • 4.07 GB

Verified: 4 years ago

Download (4.07 GB)

This asset is only available as a PickleTensor which is a deprecated and insecure format. We caution against using this asset until it can be converted to the modern SafeTensor format.

Details

Type

Checkpoint Trained

Stats

3,633

Reviews

Very Positive

(256)

Published

Nov 16, 2022

Base Model

SD 1.5

Hash

AutoV2

9DADE82620

About this version

default creator card background decoration

259

salt

Joined Nov 18, 2022

License:

CreativeML Open RAIL-M Addendum

Waifu Diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.

The model originally used for fine-tuning is Stable Diffusion 1.4, which is a latent image diffusion model trained on LAION2B-en. The current model has been fine-tuned with a learning rate of 5.0e-6 for 10 epochs on 680k anime-styled images.

See here for an in-depth overview of Waifu Diffusion 1.3.

Team Members and Acknowledgements

This project would not have been possible without the incredible work by the CompVis Researchers.

In order to reach us, you can join our Discord server.

Originally posted to HuggingFace