Signal Dynamics in Diffusion Models: Enhancing Text-to-Image Alignment through Step Selection
Keywords: Visual Generative AI, Diffusion Model, Text-to-Image Alignment
Abstract: 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 diffusion 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, achieving state-of-the-art performance. Our results highlight the importance of a judicious choice of sampling stage to improve diffusion performance and overall image alignment.
Primary Area: generative models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9929
Loading