返回文献探索AI 摘要
Paper · arXiv 2409.15997
Improvements to SDXL in NovelAI Diffusion V3
Juan Ossa, Eren Doğan, Alex Birch, F. Johnson
12 upvotesSeptember 24, 2024arXiv 预印本
Changes to SDXL were implemented in the training of NovelAI Diffusion V3 to improve anime image generation.
SDXLNovelAI Diffusionanime image generation
Abstract
In this technical report, we document the changes we made to SDXL in the process of training NovelAI Diffusion V3, our state of the art anime image generation model.