One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls

Minghui Hu, Jianbin Zheng, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 7331-7340

It is well known that many open-released foundational diffusion models have difficulty in generating images that substantially depart from average brightness despite such images being present in the training data. This is due to an inconsistency: while denoising starts from pure Gaussian noise during inference the training noise schedule retains residual data even in the final timestep distribution due to difficulties in numerical conditioning in mainstream formulation leading to unintended bias during inference. To mitigate this issue certain eps-prediction models are combined with an ad-hoc offset-noise methodology. In parallel some contemporary models have adopted zero-terminal SNR noise schedules together with v-prediction which necessitate major alterations to pre-trained models. However such changes risk destabilizing a large multitude of community-driven applications anchored on these pre-trained models. In light of this our investigation revisits the fundamental causes leading to our proposal of an innovative and principled remedy called One More Step (OMS). By integrating a compact network and incorporating an additional simple yet effective step during inference OMS elevates image fidelity and harmonizes the dichotomy between training and inference while preserving original model parameters. Once trained various pre-trained diffusion models with the same latent domain can share the same OMS module.