đ Moe Diffusion
This project aims to enhance the generation of moe characters as most other models struggle in this area.
đ Quick Start
The Moe Diffusion model is designed to generate high - quality moe characters. You can start using it by following the steps in the "Usage" section.
⨠Features
- Improved Moe Character Generation: Specialized in creating moe - style characters.
- Multiple Versions: Different versions offer various levels of control and styles.
- High - Resolution Support: Capable of generating images up to 1536x1536 resolution.
đĻ Installation
No specific installation steps are provided in the original README.
đģ Usage Examples
Basic Usage
Use CLIP skip 2 (or none/1 for SDXL). It is recommended to use a standard resolution such as 832x1144 (up to 1536x1536 for v1.3).
Positive Prompt Example:
masterpiece, best quality, (child:1.4), 1girl, solo, full body, night, purple kimono, japanese clothes, barefoot, obi, bare legs, braided ponytail, feet, mole, toes, collarbone, toenails, electricity, looking at viewer, night sky, holding weapon, holding, holding polearm, floating, sakura, petals
Negative Prompt Example:
lowres, worst quality, low quality, old, early, bad anatomy, bad hands, 4koma, comic, greyscale, censored, jpeg artifacts, aged up
All examples were generated using a custom workflow in ComfyUI and weren't edited using inpainting. You can load the workflow by either importing the example images or importing the workflow directly.
Advanced Usage
For better results, use longer prompts. Shorter prompts (less than 10 tags) may lead to lower - quality images.
đ Documentation
Current Version (v1.3)
- Based on Illustrious v1.
- Resolution raised to 1536x1536.
- There are 2 versions: II - more raw, more control, suitable for LoRA; IIZ - default style, easier to use, more biased towards loli characters.
- Longer prompts are recommended for better results.
- Improved composition and prompt adherence (both natural to a degree and booru).
Outdated Versions
- v0.4.3: Fixed color issue, general improvements.
- v0.5.3: Integrated VAE, file size reduced, CLIP force reset fix.
- v0.6.3: Style improvements, added PastelMix and Counterfeit style.
- v0.7.x: Style and composition improvements.
- v0.8.x: Major improvement on higher resolutions, style improvements, flexibility and responsivity, added support for Night Sky YOZORA model.
- v0.9.x: Different approach at merging, changes at supported models.
- v2.1.X EXPERIMENTAL RELEASE: Based on Stable Diffusion 2.1 - 768. Default negative prompt: (low quality, worst quality:1.4), (bad anatomy), extra finger, fewer digits, jpeg artifacts. For positive prompt, it's good to include tags: anime, (masterpiece, best quality). Alternatively, you may achieve positive response with: (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed, anime, waifu:1.2). It's a general - purpose model with decreased ability to generate realistic images like Waifu Diffusion. Performs better at higher resolutions like 768X or 896X.
- v0.10.x: Different approach at merging, better hands, better style inheritance, some changes in supported models.
- v0.11.x: Slight changes, some changes in supported models.
- v0.13.x: Slight model stability improvements, lower weight required for prompting loli.
- v0.14.x: Many model support changes, using merging concept from v0.10 but improved, better composition and anatomy, improved multi - character generation.
- v1.1.x XL: Uses Pony XL as a base, transfers benefits of XL and tries to improve on backgrounds of Pony.
- v1.2: This is SDXL V - Pred + ZTSNR series models. Cfg: around 5. Sampler: normal Euler is suggested. Sheduler: normal or AYS. Steps: 30. You will need SwarmUI or ComfyUI to run them, and it's suggested to manually specify the model as zsnr + vpred.
đ Useful Links
- Discord: https://discord.gg/mZ3eGeNX7S
đŧī¸ Example v1.3
đ Resources
- https://huggingface.co/datasets/gsdf/EasyNegative
- https://huggingface.co/WarriorMama777/OrangeMixs
- https://huggingface.co/hakurei/waifu - diffusion - v1 - 4
- https://huggingface.co/gsdf/Counterfeit - V2.5
- https://civitai.com/models/12262?modelVersionId=14459
- https://civitai.com/models/149664/based67
- https://huggingface.co/gsdf/Counterfeit - V2.5
- https://huggingface.co/Yntec/EstheticRetroAnime
- https://huggingface.co/dwarfbum/Hassaku
- https://huggingface.co/stb/animelike2d
đ License
CreativeML OpenRAIL - M
%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)