PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion
This addresses the computational bottleneck in high-resolution text-to-image generation for users needing fast outputs, though it is incremental as it builds on existing patch-based inference.
The paper tackles the problem of slow high-resolution image generation from pre-trained diffusion models by introducing PixelRush, a training-free framework that generates 4K images in about 20 seconds, achieving a 10x to 35x speedup over state-of-the-art methods while maintaining visual quality.
Pre-trained diffusion models excel at generating high-quality images but remain inherently limited by their native training resolution. Recent training-free approaches have attempted to overcome this constraint by introducing interventions during the denoising process; however, these methods incur substantial computational overhead, often requiring more than five minutes to produce a single 4K image. In this paper, we present PixelRush, the first tuning-free framework for practical high-resolution text-to-image generation. Our method builds upon the established patch-based inference paradigm but eliminates the need for multiple inversion and regeneration cycles. Instead, PixelRush enables efficient patch-based denoising within a low-step regime. To address artifacts introduced by patch blending in few-step generation, we propose a seamless blending strategy. Furthermore, we mitigate over-smoothing effects through a noise injection mechanism. PixelRush delivers exceptional efficiency, generating 4K images in approximately 20 seconds representing a 10$\times$ to 35$\times$ speedup over state-of-the-art methods while maintaining superior visual fidelity. Extensive experiments validate both the performance gains and the quality of outputs achieved by our approach.