Animagus XL 1.0

Animagus is an anime-themed finetuned model built on top of Stable Diffusion XL, created as part of the Animagine XL series. The model merges multiple specialized checkpoints using advanced multistage methods (karcher_mean, ties_sum and task_arithmetic) and is then fine-tuned on carefully selected illustration datasets. This process delivers more stable outputs, accurate anatomy, and rich colors, while preserving the “anime” style.

• 

  View on CivitAI

• 

  Download Animagus XL 1.0

• 

  Download Animagus XL Zero

• Civitai hub
  Explore model details, community examples, and usage tips:
  View on CivitAI
• Animagus XL 1.0 (fine‑tuned)
  The final anime‑optimized model after fine‑tuning on curated illustration datasets.
  Download Animagus XL 1.0
• Animagus XL Zero (raw merge)
  A direct merge of all source checkpoints before fine‑tuning.
  Download Animagus XL Zero

Model Details

• Model type: diffusion-based text-to-image
• Base checkpoint: Stable Diffusion XL 1.0
• Initial finetuned models: Animagine XL 3.1 and Animagine XL 4.0 Opt
• License: CreativeML Open RAIL++-M

Training Pipeline

• Karcher mean (Riemannian center of mass): a generalization of the arithmetic mean to curved spaces (Riemannian manifolds), finding the point that minimizes the sum of squared Riemannian distances to all checkpoints.
• subtract and add_difference to preserve the unique characteristics of each checkpoint
• fallback and task_arithmetic for flexible combination of UNet, VAE, and CLIP components

• pixiv – a collection of illustrations with high aesthetic scores
• latum – expressive artworks with pleasant tones and fine line work
• artists – artworks by asou, hara_harayutaka, hiroki_yyqw7151 in a vanilla anime screencap style
• aiga – AI-generated images with high aesthetic scores
• anime – screenshots and illustrations from anime and hentai

Note: UNet and CLIP were fine-tuned separately due to an initial configuration error.

Styles Reference

Note: This list was gathered from models used during merging and serves as a helpful starting point, but not all tags are guaranteed to work equally well. Feel free to experiment and discover which styles best suit your use case.

Usage Guidelines

• https://huggingface.co/cagliostrolab/animagine-xl-4.0
• https://huggingface.co/cagliostrolab/animagine-xl-3.1

Recipe