Diffusion Models without Classifier-free Guidance
This addresses a key bottleneck in diffusion models for image generation by eliminating the need for CFG, offering a plug-and-play solution that improves efficiency and quality for researchers and practitioners.
The paper tackles the reliance on Classifier-free Guidance (CFG) in diffusion models by introducing Model-guidance (MG), a novel training objective that removes CFG while achieving state-of-the-art performance, such as an FID of 1.34 on ImageNet 256 benchmarks, with doubled inference speed and accelerated training.
This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data distribution to incorporating the posterior probability of conditions. The proposed technique originates from the idea of CFG and is easy yet effective, making it a plug-and-play module for existing models. Our method significantly accelerates the training process, doubles the inference speed, and achieve exceptional quality that parallel and even surpass concurrent diffusion models with CFG. Extensive experiments demonstrate the effectiveness, efficiency, scalability on different models and datasets. Finally, we establish state-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34. Our code is available at https://github.com/tzco/Diffusion-wo-CFG.