6 papers · 1 filter
DICE: Distilling Classifier-Free Guidance into Text Embeddings
Zhenyu Zhou, Defang Chen, Can Wang +2
Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely…
Knowledge Distillation with Refined Logits
Wujie Sun, Defang Chen, Siwei Lyu +3
Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this pap…
Conditional Image Synthesis with Diffusion Models: A Survey
Zheyuan Zhan, Defang Chen, Jian-Ping Mei +5
Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has bec…
Simple and Fast Distillation of Diffusion Models
Zhenyu Zhou, Defang Chen, Can Wang +2
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient…
Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
Zhenyu Zhou, Defang Chen, Can Wang +1
Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number…
A Geometric Perspective on Diffusion Models
Defang Chen, Zhenyu Zhou, Jian-Ping Mei +3
Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochast…