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.

• Anthony Mercurio
• Salt
• Cafe

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

Originally posted to HuggingFace