Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation

2025-10-06 · Zijing Hu, Yunze Tong, Fengda Zhang, Junkun Yuan, Jun Xiao, Kun Kuang arxiv

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation is associated with synchronous denoising, where all pixels simultaneously evolve from random noise to clear images. As a result, during generation, the prompt-related regions can only reference the unrelated regions at the same noise level, failing to obtain clear context and ultimately impairing text-to-image alignment. To address this issue, we propose asynchronous diffusion models -- a novel framework that allocates distinct timesteps to different pixels and reformulates the pixel-wise denoising process. By dynamically modulating the timestep schedules of individual pixels, prompt-related regions are denoised more gradually than unrelated regions, thereby allowing them to leverage clearer inter-pixel context. Consequently, these prompt-related regions achieve better alignment in the final images. Extensive experiments demonstrate that our asynchronous diffusion models can significantly improve text-to-image alignment across diverse prompts. The code repository for this work is available at https://github.com/hu-zijing/AsynDM.

📄 PDF Abstract BibTeX arXiv:2510.04504

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image Generation

Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation

2026-03-10 · Junyi An, Chao Qu, Yun-Fei Shi, Zhijian Zhou 외 arxiv

Recent 3D molecular generation methods primarily use asynchronous auto-regressive or synchronous diffusion models. While auto-regressive models build molecules sequentially, they're limited by a short horizon and a discr…

Step-level Denoising-time Diffusion Alignment with Multiple Objectives

2026-04-15 · Qi Zhang, Dawei Wang, Shaofeng Zou arxiv

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however…

Reinforcement Learning

Text-Guided Texturing by Synchronized Multi-View Diffusion

2023-11-21 · Yuxin Liu, Minshan Xie, Hanyuan Liu, Tien-Tsin Wong

This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existing methods usually employ a project-and-…

Texture Synthesis

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

2025-09-08 · Xiangwei Shen, Zhimin Li, Zhantao Yang, Shiyi Zhang 외 arxiv

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denois…

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

2024-07-02 · Zhiyuan Ma, Yuxiang Wei, Yabin Zhang, Xiangyu Zhu 외

By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have …

Prediction Text to 3D