Anime

🚀 2D-Mix

2D-Mix is a text - to - image model created by merging multiple checkpoints using Automatic1111 Checkpoint Merger. It combines Anything - V3.0 - pruned, Waifu - v1 - 3 - float16, NAI, sd - v1 - 5 - pruned - emaonly, and trinart_stable_diffusion_epoch3.

✨ Features

• Tags: stable - diffusion, text - to - image
• Library: diffusers
• Pipeline: text - to - image
• Datasets:
  • Guizmus/AnimeChanStyle
  • skytnt/fbanimehq
  • skytnt/anime - segmentation
  • Nerfgun3/bad_prompt
  • Nerfgun3/shatter_style
  • Nerfgun3/ouroboros_embeddings

💻 Usage Examples

Basic Usage

Here are some examples of using the 2D - Mix model:

Example 1

Prompt: Christina Hendricks (realistic photo:1.0), (masterpiece:1.0), (highest quality:1.0), (high quality:1.0), (detailed face:1.0), (detailed eyes:1.0), highres Negative prompt: text, signature, Doll, deformed, asymmetric, cropped, censored, frame, mock - up, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, worst quality, low quality, normal quality, jpeg artifacts, watermark, username, blurry, artist name Steps: 30, Sampler: Euler a, CFG scale: 9, Seed: 365192021, Size: 512x512, Model hash: 63ac6702, Model: 2D - Mix, ENSD: 31337

Example 2

Prompt: beautiful geisha in full sky blue kimono facing away from the camera looking back over shoulder with arm extended to the right, elegant, vintage, ornate, art nouveau, complimentary colors, painted by Will Murai, Artgerm, Alphonse Mucha, Akihiko Yoshida, dramatic color, Phil Noto, Krenz Cushart, digital painting Negative prompt: text, signature, Doll, deformed, asymmetric, cropped, censored, frame, mock - up, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, worst quality, low quality, normal quality, jpeg artifacts, watermark, username, blurry, artist name Steps: 40, Sampler: Euler a, CFG scale: 11, Seed: 3633019598, Size: 512x512, Model hash: 63ac6702, Model: 2D - Mix, Clip skip: 2, ENSD: 31337

Example 3

Prompt: woman in colorful kimono AND man in coloful yukata Negative prompt: gray, hazy, text, signature, cropped Steps: 33, Sampler: Euler, CFG scale: 15, Seed: 4230961168, Size: 512x512, Model hash: 63ac6702, Model: 2D - Mix, Clip skip: 5, ENSD: 31337

Example 4

Prompt: woman in colorful kimono AND man in coloful yukata Negative prompt: gray, hazy, text, signature, cropped Steps: 33, Sampler: Euler, CFG scale: 15, Seed: 4230961169, Size: 512x512, Model hash: 63ac6702, Model: 2D - Mix, Clip skip: 5, ENSD: 31337

📚 Documentation

The dataset used for making the 2D - Mix model is Guizmus/AnimeChanStyle.

The images in this dataset were created by users of Stable Diffusion discord using CreativeML - OpenRail - M licenced models. 90 pictures were manually captioned with their content and the suffix ",AnimeChan Style".

The collection process was made public for less than a day until enough variety was introduced to train a style corresponding to the different members of this community through the Dreambooth method.

The captioned pictures are available in this zip file.

📄 License

This model is licensed under creativeml - openrail - m.