๐ Mitsua Diffusion CC0 Model
Mitsua Diffusion CC0 is a latent text - to - image diffusion model. It addresses the need for an ethical text - to - image generation by training its U - Net from scratch using specific types of images. It serves as a base model for AI VTuber Elan Mitsua's activities.
๐ Quick Start
This version is deprecated. Please use Mitsua Diffusion One, which is a successor of this model.
โจ Features
- Ethical Training: Mitsua Diffusion CC0's U - Net is trained from scratch using only public domain/CC0 or copyright images with permission for use.
- Borrowed Components: Text Encoder and VAE are borrowed from Stable Diffusion v2.1 base.
- Base for AI VTuber: It will be used as a base model for AI VTuber Elan Mitsua๐๏ธโs activity.
โ ๏ธ Important Note
Currently the model has super low visual quality and limited diversity.
๐ก Usage Tip
You can join her training on Twitter! Further training will be done in a fully opt - in basis. If you are interested in, please click here to submit an opt - in application.
๐ฆ Installation
No installation steps are provided in the original document.
๐ป Usage Examples
No code examples are provided in the original document.
๐ Documentation
Mitsua Diffusion CC0 is a latent text - to - image diffusion model. The model uses a unique approach of training its U - Net from scratch with specific image sources. The text encoder and VAE are sourced from Stable Diffusion v2.1 base. It aims to be a base for AI VTuber Elan Mitsua's activities.
You can check here to all prompts to generate these images.
Training Data Sources
All data was obtained ethically and in compliance with the site's terms and conditions. No copyright images are used in the training of this model without the permission, and no AI generated images are in the dataset.
| Property |
Details |
| Traditional Artwork |
MET Museum Open Access, Smithsonian Open Access, Cleveland Museum of Art Open Access, National Gallery of Art Open Access, ArtBench - 10 (public domain subset) |
| CC0 Photos |
Flickr, Wikimedia Commons |
| CC0 NFTs |
goblintown.nft, mfer, tubby - cats, Timeless. Their work is released under a CC0 license, but if you are considering using this model to create a work inspired by their NFT and sell it as NFT, please consider paying them a royalty to help the CC0 NFT community grow. |
| CC0 VRM models |
made by VRoid Project, pastelkies, yomox9 (all CC0 subset). A bunch of synthesized images dataset rendered with various poses and camera angles were generated. |
| Copyright images |
Generative and Visual Artworks made by Rhizomatiks |
Approx 11M images in total with data augmentation.
๐ง Technical Details
No specific technical details (more than 50 - word description) are provided in the original document.
๐ License
This model uses the Creative Open - Rail++ - M License.
โโ โMitsua Diffusion CC0โ means most of the training data is CC0. the model license itself is NOT CC0.โโ
The CreativeML OpenRAIL++ - M License specifies:
- You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
- 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.
- 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.
Developed by
- Stable Diffusion 2.1: Robin Rombach, Patrick Esser
- Mitsua Diffusion CC0 : Abstract Engine dev team
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)