CVAILGSep 24, 2024

Improvements to SDXL in NovelAI Diffusion V3

arXiv:2409.15997v21 citationsh-index: 3
Originality Synthesis-oriented
AI Analysis

This work addresses image generation for anime enthusiasts, but appears incremental as it builds on SDXL.

The authors tackled improving the SDXL model for anime image generation, resulting in NovelAI Diffusion V3, which they claim as state-of-the-art.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes