Rethinking cluster-conditioned diffusion models for label-free image synthesisby Nikolas Adaloglou, Tim Kaiser, Felix Michels, Markus…
Learning to Find Missing Video Frames with Synthetic Data Augmentation: A General Framework and Application…
Structure-Guided Adversarial Training of Diffusion Modelsby Ling Yang, Haotian Qian, Zhilong Zhang, Jingwei Liu, Bin…
Accelerating Diffusion Sampling with Optimized Time Stepsby Shuchen Xue, Zhaoqiang Liu, Fei Chen, Shifeng Zhang,…
Contextualized Diffusion Models for Text-Guided Image and Video Generationby Ling Yang, Zhilong Zhang, Zhaochen Yu,…
Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversionby Xuantong Liu, Tianyang…
The Surprising Effectiveness of Skip-Tuning in Diffusion Samplingby Jiajun Ma, Shuchen Xue, Tianyang Hu, Wenjia…
Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Controlby Masatoshi Uehara, Yulai Zhao, Kevin Black, Ehsan…
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitchingby Zizheng Pan, Bohan Zhuang, De-An…
SDXL-Lightning: Progressive Adversarial Diffusion Distillationby Shanchuan Lin, Anran Wang, Xiao YangFirst submitted to arxiv on:…