Text-to-Image Alignment in Denoising-Based Models through Step Selection
This addresses text-image misalignment issues in visual generative AI, which is an incremental improvement over existing methods.
The paper tackles the problem of text-to-image alignment in denoising-based generative models by selectively enhancing signal at critical denoising steps, achieving state-of-the-art performance on Diffusion and Flow Matching models.
Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image generation based on input semantics. Our approach addresses the shortcomings of early-stage signal modifications, demonstrating that adjustments made at later stages yield superior results. We conduct extensive experiments to validate the effectiveness of our method in producing semantically aligned images on Diffusion and Flow Matching model, achieving state-of-the-art performance. Our results highlight the importance of a judicious choice of sampling stage to improve performance and overall image alignment.