Improvements to SDXL in NovelAI Diffusion V3
Juan Ossa, Eren Do\u{g}an, Alex Birch, F. Johnson
TL;DR
This paper details the modifications made to the SDXL model during the training of NovelAI Diffusion V3, a cutting-edge anime image generation system.
Contribution
It introduces specific improvements to SDXL tailored for enhancing anime image generation in NovelAI Diffusion V3.
Findings
Enhanced image quality in anime generation
Improved training stability and efficiency
Better model generalization for anime styles
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Optical Network Technologies
MethodsDiffusion