Illustrious-XL
Danbooru-trained SDXL model family that became the dominant base for anime image generation.
About
Anime and illustration generation largely standardized on Illustrious-XL, OnomaAI's family of SDXL models trained on Danbooru-style tagged data. The v1.0 release, trained in July 2024 with data through June 2024 and built up from the v0.1 checkpoint, extends native resolution to 1536x1536 while handling everything from 512x512 upward, and it responds to both booru tag prompting and natural language descriptions. Its real significance is as a foundation: on Hugging Face alone v1.0 lists more than 90 finetunes and nearly 100 merges, and on Civitai the Illustrious line underpins a large share of the popular anime checkpoints and LoRAs that succeeded the Pony Diffusion era. Weights are distributed under the SDXL license, CreativeML Open RAIL++-M, which permits commercial use subject to its use restrictions, and OnomaAI operates a hosted generation platform at illustrious-xl.ai alongside research notes on the model series. Running it locally takes any SDXL-capable frontend such as ComfyUI or the WebUI variants on a consumer GPU, and no GitHub repository exists since distribution is checkpoint based.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Image Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- CreativeML Open RAIL++-M
- Added
- Jul 29, 2026
Related Tools
State-of-the-art open image generation model by Black Forest Labs with rectified flow transformers.
Next-generation image generation model by Black Forest Labs.
Bilingual text-to-image diffusion transformer by Tencent with Chinese and English support.
Zero-shot identity-preserving image generation from a single face photo.
Image prompt adapter for pre-trained text-to-image diffusion models.
Neural network architecture for adding spatial control to diffusion models.