Elucidating the Preconditioning in Consistency Distillation

K Zheng, G He, J Chen, F Bao, J Zhu - arxiv preprint arxiv:2502.02922, 2025 - arxiv.org
Consistency distillation is a prevalent way for accelerating diffusion models adopted in
consistency (trajectory) models, in which a student model is trained to traverse backward on …

Consistency Diffusion Bridge Models

G He, K Zheng, J Chen, F Bao, J Zhu - arxiv preprint arxiv:2410.22637, 2024 - arxiv.org
Diffusion models (DMs) have become the dominant paradigm of generative modeling in a
variety of domains by learning stochastic processes from noise to data. Recently, diffusion …

Exploring the Design Space of Diffusion Bridge Models via Stochasticity Control

S Zhang, Y Cheng, X Kong, GV Steeg - arxiv preprint arxiv:2410.21553, 2024 - arxiv.org
Diffusion bridge models effectively facilitate image-to-image (I2I) translation by connecting
two distributions. However, existing methods overlook the impact of noise in sampling SDEs …

[PDF][PDF] Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Generative Models

S Chen, T Wang, X Song, B **g, J Yang, J Song… - osf.io
1Zhejiang University, A1033439225@ gmail. com 2**'an Jiaotong-Liverpool University,
Tianyang. Wang21@ student. xjtlu. edu. cn 3Emory University, songxinyuan@ pku. edu. cn …