From 194751939763b8ba82913bcb7bbd40217d0611df Mon Sep 17 00:00:00 2001 From: Akumi Chan <65241893+GripenANM@users.noreply.github.com> Date: Tue, 25 Oct 2022 13:23:18 -0700 Subject: [PATCH 1/2] Update Weights Readme.md to v1.3 model cloned huggingface model card --- docs/en/weights/README.md | 52 +++++++++++++++++++++++++++++++++------ 1 file changed, 44 insertions(+), 8 deletions(-) diff --git a/docs/en/weights/README.md b/docs/en/weights/README.md index a141ae8..8f90bfc 100644 --- a/docs/en/weights/README.md +++ b/docs/en/weights/README.md @@ -1,15 +1,51 @@ -# Weights +--- +language: +- en +tags: +- stable-diffusion +- text-to-image +license: creativeml-openrail-m +inference: false -The following is a small list of available weights released by the Waifu Diffusion project: +--- -- Waifu Diffusion v1.2 +# Waifu Diffusion v1.3 -Release Date: 07/09/2022 +Waifu Diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning. -Steps/Epochs/Images: 5 Epochs, 56,000 Images +- [Float 16 EMA Pruned](https://huggingface.co/hakurei/waifu-diffusion-v1-3/blob/main/wd-v1-3-float16.ckpt) +- [Float 32 EMA Pruned](https://huggingface.co/hakurei/waifu-diffusion-v1-3/blob/main/wd-v1-3-float32.ckpt) +- [Float 32 Full Weights](https://huggingface.co/hakurei/waifu-diffusion-v1-3/blob/main/wd-v1-3-full.ckpt) +- [Float 32 Full Weights + Optimizer Weights (For Training)](https://huggingface.co/hakurei/waifu-diffusion-v1-3/blob/main/wd-v1-3-full-opt.ckpt) -Download: [Mirrors](./danbooru-7-09-2022/README.md) +## Model Description -License: None +The model originally used for fine-tuning is [Stable Diffusion 1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4), which is a latent image diffusion model trained on [LAION2B-en](https://huggingface.co/datasets/laion/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. -Authors: Haru (haru#1367@discord) \ No newline at end of file +[See here for an in-depth overview of Waifu Diffusion 1.3.](https://gist.github.com/harubaru/f727cedacae336d1f7877c4bbe2196e1) + +## License + +This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. +The CreativeML OpenRAIL License specifies: + +1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content +2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license +3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) +[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license) + +## Downstream Uses + +This model can be used for entertainment purposes and as a generative art assistant. + +## Team Members and Acknowledgements + +This project would not have been possible without the incredible work by the [CompVis Researchers](https://ommer-lab.com/). + +- [Anthony Mercurio](https://github.com/harubaru) +- [Salt](https://github.com/sALTaccount/) +- [Cafe](https://twitter.com/cafeai_labs) + +In order to reach us, you can join our [Discord server](https://discord.gg/touhouai). + +[![Discord Server](https://discordapp.com/api/guilds/930499730843250783/widget.png?style=banner2)](https://discord.gg/touhouai) From e1e416a5b9a47540325d297ea56b17dbaa0796ed Mon Sep 17 00:00:00 2001 From: Akumi Chan <65241893+GripenANM@users.noreply.github.com> Date: Tue, 25 Oct 2022 13:31:22 -0700 Subject: [PATCH 2/2] Removed Huggingface metadata table --- docs/en/weights/README.md | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/docs/en/weights/README.md b/docs/en/weights/README.md index 8f90bfc..db10ac3 100644 --- a/docs/en/weights/README.md +++ b/docs/en/weights/README.md @@ -1,14 +1,3 @@ ---- -language: -- en -tags: -- stable-diffusion -- text-to-image -license: creativeml-openrail-m -inference: false - ---- - # Waifu Diffusion v1.3 Waifu Diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.