Animagus XL 1.0

Animagus is an anime-themed finetuned model built on top of Stable Diffusion XL, created over the Animagine XL series. The model merges over 20 specialized checkpoints using multistage merging methods, and then finetuned on carefully selected illustration datasets. This results in more stable outputs, accurate anatomy, and rich colors, while preserving the anime style.

Styles Reference

You can influence the visual style of generated images by including artist or style tags in your prompt. For a curated list of artist tags that have been tested with Animagus (compiled from the various checkpoints used in the merge), download the reference here:

Download artist list:
https://huggingface.co/rityak/animagus/raw/main/artist_list.txt

Usage Guidelines

The usage guidelines will be the same as for Animagine 3.1 and 4.0. For more details, please refer to:
- cagliostrolab/animagine-xl-4.0
- cagliostrolab/animagine-xl-3.1

Assets & Detailes

You can access the full merge recipe and the raw (un-fine-tuned) Animagus model on Hugging Face:
👉 rityak/animagus

This includes:
- The complete YAML recipe used to merge over 20 anime-themed checkpoints
- The resulting merged checkpoint (pre-fine-tuning), ready for experimentation

Note: The raw merged model has not undergone fine-tuning and may produce noisier or less refined outputs. It’s intended as a base for further training, customization, or analysis.

Для русскоязычных пользователей

Если вы интересуетесь нейросетями, LLM, Stable Diffusion и хотите пообщаться в тёплой компании, присоединяйтесь к нашему ламповому чату:

👉 @ritya_smokeroom