Lune

ICLR2025

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Gihyun Kwon, Jong Chul Ye

2025年份

摘要

Multi-concept Generation Results from TweedieMix. Our model can generate highquality multi-concept generation results on both of image and video domains. More results can be found in the experiment section.