Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation
Quan Dao, Hao Phung, Trung Tuan Dao, Dimitris N. Metaxas, Anh Tran
Abstract
Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset.
BibTeX
@article{Dao_Phung_Dao_Metaxas_Tran_2025, title={Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32269}, DOI={10.1609/aaai.v39i3.32269}, abstractNote={Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset.}, number={3}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Dao, Quan and Phung, Hao and Dao, Trung Tuan and Metaxas, Dimitris N. and Tran, Anh}, year={2025}, month={Apr.}, pages={2654-2662} }