VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
Paper
•
2412.20800
•
Published
•
10
Generation Quality Enhancement
-
-
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
Paper • 2501.06751 • Published • 31 -
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Paper • 2501.09732 • Published • 70 -
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
Paper • 2501.09755 • Published • 34 -
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
Paper • 2502.12146 • Published • 15