UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
This work addresses quality and efficiency issues in text-to-image generation for users of diffusion models, representing an incremental improvement through a novel hybrid approach.
The authors tackled the limitations of latent diffusion models, such as inferior visual quality and inefficient inference, by introducing UniFL, a unified feedback learning framework that improved user preference by 17% over ImageReward for generation quality and outperformed LCM and SDXL Turbo by 57% and 20% in general preference with 4-step inference.
Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior visual quality, inadequate aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL consists of three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which accelerates inference. In-depth experiments and extensive user studies validate the superior performance of our method in enhancing generation quality and inference acceleration. For instance, UniFL surpasses ImageReward by 17% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57% and 20% general preference with 4-step inference.