ArtiWaifu Diffusion - V2.0 API Documentation

🏷 Model Information 🏷

• Developed by: Euge

• Funded by: Neta.art

• Model type: Generative text-to-image model

• Finetuned from model: ArtiWaifu Diffusion 1.0

• License: Fair AI Public License 1.0-SD

🔥 Highlights 🔥

• More art styles (9000+) and characters (6000+), ~1.5x than 1.0.

• More stable anatomy

• More data support for painting styles

• Experimentally added some amazing AI artist styles: by shiroski, by trickortreat, by nyalia, by pasota, by xerganea, and by yandantui.

🚀 Dataset Source 🚀

• Subset of Danbooru (2.3M). Selected by aesthetic score using Waifu Scorer V3.

• Subset of Pixiv (0.1M). Hand-selected.

• Others (0.1M).

👀 Future Plan 👀

• Apply stronger training strategies.

• Continue adding more and more high-quality data.