SDXL Image Local Cloud Image input

Animagine XL

Specialized SDXL fine-tune for high-quality anime illustration with extensive character knowledge and structured prompting

$0.003

per image in the cloud

$0

on your own GPU

Run it free Use it in Claude or the API

Overview

Animagine XL is an open-source anime-focused model developed by [Cagliostro Research Lab](https://cagliostrolab.net/), fine-tuned from Stable Diffusion XL. It specializes in generating high-quality anime illustrations with improved anatomy, strong character recognition, and consistent art style.

Key Features

Anime Specialization: Purpose-built for anime aesthetics with vibrant colors and clean line work
Character Knowledge: Extensive training on popular anime characters for accurate fan art generation
Improved Anatomy: Enhanced hand rendering and body proportions compared to base SDXL
Structured Prompting: Supports organized tag-based prompts for precise control over outputs

Best For

Anime character illustrations and fan art
Original anime-style character designs
Consistent anime aesthetic across multiple generations
Projects requiring recognizable anime art styles
Both SFW and NSFW anime content

Prompt Tips

Describe your scene naturally. The model excels at translating detailed descriptions into anime-style images.
Specifying the anime era or style you want (e.g., "modern anime", "90s anime aesthetic", "shonen style") helps guide the output
For character art, describe personality, expression, and outfit for more dynamic and expressive results
The model follows detailed prompts closely, so describe the full composition for best results

Use it

Three ways to run Animagine XL

Download Imference Desktop and open it.
In Local models, pick Animagine XL. It downloads once.
Write a prompt and press Generate. Free, on your GPU.

Get the app

Make an image with Animagine XL ("anime-v1"): a lighthouse on a cliff at dusk, cinematic light

curl https://imference.com/generate \
  -H "Authorization: Bearer $IMFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "anime-v1",
       "format_code": "square",
       "prompt": "a lighthouse on a cliff at dusk, cinematic light"}'

Claude needs the MCP server. API details in the reference.

Specs