Rectified Flow is a promising way for accelerating pre-trained diffusion models. However, the generation quality of prior fast flow-based models on Stable Diffusion (such as InstaFlow) is unsatisfactory. In this work, we did several improvements to the original reflow pipeline to significantly boost the performance of flow-based fast SD. Our new model learns a piecewise linear probability flow which can efficiently generate high-quality images in just 4 steps, termed piecewise rectified flow (PeRFlow). Moreover, we found the difference of model weights can be used as a plug-and-play accelerator module on a wide-range of SD-based models.

Specifically, PeRFlow has several features:

• Fast Generation : PeRFlow can generate high-fidelity images in just 4 steps. The images generated from PeRFlow are more diverse than other fast-sampling models (such as LCM). Moreover, as PeRFlow is a continuous probability flow, it supports 8-step, 16-step, or even higher number of sampling steps to monotonically increase the generation quality.
• Efficient Training: Fine-tuning PeRFlow based on SD 1.5 converges in just 4,000 training iterations (with a batch size of 1024). In comparison, previous fast flow-based text-to-image model, InstaFlow, requires 25,000 training iteration with the same batch size in fine-tuning. Besides, PeRFlow does not require heavy data generation for reflow.
• Compatible with SD Workflows: PeRFlow works with various stylized LORAs and generation/editing pipelines of the pretrained SD model. As a plug-and-play module, can be directly combined with other conditional generation pipelines, such as ControlNet, IP-Adaptor, multi-view generation.
• Classifier-Free Guidance : PeRFlow is fully compatible with classifier-free guidance and supports negative prompts, which are important for pushing the generation quality to even higher level. Empirically, the CFG scale is similar to the original diffusion model.