SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 DiffusionD

Read original source ↗ Open in workspace

recordType

paper

region

Global