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.
Improvements to SDXL in NovelAI Diffusion V3
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis (2023)63% match
- Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation (2024)57% match
- Real-World Image Variation by Aligning Diffusion Inversion Chain (2023)56% match
- MMDiff: Extending Diffusion Transformers for Multi-Modal Generation (2026)56% match
- Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (2024)55% match
- Latent Denoising Diffusion GAN: Faster sampling, Higher image quality (2024)55% match
- Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation (2025)55% match
- Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers (2024)55% match