Moediffusionplusplus

🚀 MoeDiffusion++

This project is a text - to - image model that combines multiple models to generate high - quality anime - style images. It offers different versions (V1 and V2) with various features and is suitable for generating images of specific styles, such as black - haired ponytail girls.

🚀 Quick Start

You can run this model on the Colab WebUI. Rewrite the following line of this notebook following the instructions posted here.

!aria2c --summary-interval=10 -x 16 -s 16 --allow-overwrite=true -Z https://huggingface.co/JosephusCheung/ACertainModel/resolve/main/ACertainModel-half.ckpt

✨ Features

Model Composition

• V1: It is composed of MoeDiffusion 1.0 + (HassanBlend 1.5 - VMix03) * 0.2.
• V2: It is a combination of MoeDiffusion 0.6, HassanBlend 1.5 0.2, and VMix03 0.2.

Other Features

• NSFW Resistance: Since the sfw version is merged, nsfw outputs are less likely to appear, but they may still show up occasionally.
• Face Generation: By adding the prompt art by yaguru magiku with appropriate strength, you can get faces in the YaguruMagiku style.
• Color Rendering: Adding a vae might improve the coloring, but the merged model already has decent coloring.

💻 Usage Examples

Basic Usage

You can use the following prompt to generate images:

art by yaguru magiku, A teenage girl wearing a black yukata, angry smile, in the style of Kyoto Animation in the 2010s, official art, ((((black hair)), eyes of Haruhi Suzumiya, face of Haruhi Suzumiya)), beautiful symmetric face, ponytail, in the universe with stars and galaxies, psychedelic art, rainbows, transcendence, alone, solo, 8k, posing of Haruhi Suzumiya
Negative prompt: low quality, bad face, ((ugly face)), asymmetric face, ((((bad anatomy)))), ((bad hand)), too many fingers, missing fingers, too many legs, lowres, jpeg artifacts, (((text))), logo, signature, sad face, ((loli)), twintails, plaits, pajamas, blushing, boy, adult, bells, fanart, pixiv, card game, ahoge, ribbon, weapons, armors, tools, white background, simple background
Steps: 50
Sampler: Euler a
CFG scale: 7
Size: 768x768

Advanced Usage

For different styles and scenarios, you can adjust the prompt, negative prompt, steps, sampler, CFG scale, and size. For example, to generate a beach - themed image:

art by yaguru magiku, A teenage girl wearing a black bikini, angry smile, in the style of Kyoto Animation in the 2010s, official art, ((((black hair)), eyes of Haruhi Suzumiya, face of Haruhi Suzumiya)), beautiful symmetric face, ponytail, at a beach on a summer day, ((alone, solo)), 8k, posing of Haruhi Suzumiya, vivid colors
Negative prompt: low quality, bad face, ((ugly face)), asymmetric face, ((((bad anatomy)))), ((bad hand)), too many fingers, missing fingers, too many legs, lowres, jpeg artifacts, (((text))), logo, signature, sad face, ((loli)), twintails, plaits, pajamas, jackets, blushing, boy, adult, bells, fanart, pixiv, card game, ahoge, ribbon, weapons, armors, tools, white background, simple background, sepia, grayscale, greyscale, bruises
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 3233330301, Size: 768x768

📄 License

General Information

The model is licensed under The Libertarian OpenRAIL License.

Caution

Since the uploader is a Japanese native, in the event of any differences in meaning between the original Japanese version and a translation, the original Japanese version takes precedence.

Summary

It is a CreativeML Open RAIL - M, interpreted and reconstructed under a libertarian manner. The restrictions of CreativeML Open RAIL - M are considered to be valid under such interpretation.

Main Differences from the Original CreativeML Open RAIL - M License

• Legal Judgment: The violation of law or regulation will be judged by and only by your conviction per the presumption of innocence (unless you are convicted, it is not enough to claim it is illegal for the Licensor, even if it looks like it).
• Output Distribution: Outputs generated by the Model or Derivatives of the Model must be distributed under public domain (CC0 1.0), to ensure not only you but anyone can (re)use it freely.
• Derivative Model Requirements: Derivatives of the Model will always have to include - at minimum - the same use - based restrictions and the same open permissions.

Full License

• Japanese Version: Refer to License_ja.md.
• English Version: Refer to License_en.md.