đ Moe Diffusion
This project aims to enhance the generation of moe characters as most other models struggle in this area. It provides better results for creating such characters and offers multiple versions to meet different needs.
đ Quick Start
The goal of this project is to improve generation of moe characters since most of other models are not good at it.
Support me: https://boosty.to/moefussion
Some of the models can be used online on these platforms:
Aipictors (Japanese) - https://www.aipictors.com
⨠Features
- Improved Moe Character Generation: Focuses on better creating moe characters compared to other models.
- Multiple Model Versions: Offers different versions like v1.3 with various styles and capabilities.
- High - Resolution Support: Supports high resolutions up to 1536x1536 in v1.3.
đĻ Installation
Not provided in the original README, so this section is skipped.
đģ Usage Examples
Basic Usage
Use CLIP skip 2 (or none/1 for SDXL).
It is recommended to use 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 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.
đ Documentation
Useful links
Discord: https://discord.gg/mZ3eGeNX7S
About
Current
v1.3
Illustrious v1 based.
Resolution raised to 1536x1536.
There are 2 versions II - more raw, more control, suitable for LoRA and IIZ - default style, easier to use, more bias to loli chara.
It's better to use longer prompts for better results, shorter (sub 10 tags) may result in lower quality.
Improved composition and prompt adherence (both natural to a degree and booru).
Outdated
- 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 improvements. 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, you might find v0.8.x versions better. Changes at supported models.
- v2.1.X EXPERIMENTAL RELEASE: Stable Diffusion 2.1 - 768 based. 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). Though it's Loli Diffusion model it's quite general purpose. The ability to generate realistic images as Waifu Diffusion can was intentionally decreased. This model 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. Prompting loli requires lower weight now.
- v0.14.x: Many model support changes. Using merging concept from v0.10 but improved as 13 and 11 had unwanted side effects. Composition and anatomy should be more coherent now. 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, while they should get autodetected it's suggested to manually specify the model as zsnr+vpred.
Example v1.3
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
The project uses the creativeml-openrail-m license.
| Property |
Details |
| Pipeline Tag |
text-to-image |
| Tags |
art, anime |
| Library Name |
diffusers |
%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)