Abstract: Diffusion models have shown great promise in synthesizing visually appealing images. However, it remains challenging to condition the synthesis at a fine-grained level, for instance, ...
Diffusion Embedder is a simple recipe to train text encoders directly from diffusion LMs without the need of any transformation step. Diffusion LMs naturally possess bidirectional attention, which is ...
The main challenge of universal image restoration tasks is handling different degradation images at once. In this work, we propose a selective hourglass mapping strategy based on conditional diffusion ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results