Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models

2026-09-14

AI Summary

提出了一种自适应扩散控制器，通过动态调整去噪步骤数量来高效生成高质量图像，解决了固定步骤数难以平衡时间和质量的问题。

Abstract

Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity of the input text prompt. We propose an adaptive diffusion controller that dynamically adjusts the number of steps to generate high-quality images efficiently, without additional model training. By leveraging a mixture of step schedules with varying step sizes and evaluating the error term discrepancy at each timestep, our method transitions between schedules to optimize performance. Experiments on COCO and DiffusionDB show that our approach reduces inference time while maintaining visual fidelity, offering a more efficient alternative for text-to-image diffusion models.

Problem

• Text-to-Image
• Diffusion Models
• Denoising Steps
• Adaptive Control
• Efficiency

Innovation

• adaptive diffusion controller
• dynamic adjustment of denoising steps
• error term discrepancy
• mixture of step schedules