VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip

Wenqi Marshall Guo, Shan Du

Keywords: Image Generation, Diffusion Models, Negative Guidance

Abstract: We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step (1-8 steps) diffusion and flow-matching image and video generation models. Unlike existing approaches such as classifier-free guidance (CFG), NASA, and NAG, VSF dynamically suppresses undesired content by flipping the sign of attention values from negative prompts. Our method requires only a small computational overhead and integrates effectively with MMDiT-style architectures such as Stable Diffusion 3.5 Turbo and Flux Schnell, as well as cross-attention-based models like Wan. We validate VSF on a proposed challenging dataset, NegGenBench, with complex prompt pairs. Experimental results on our proposed dataset show that VSF significantly improves negative prompt adherence (reaching 0.420 negative score for quality settings and 0.545 for strong settings) compared to prior methods in few-step models (scored 0.320-0.380 negative score) and even CFG in non-few-step models (scored 0.300 negative score), while maintaining competitive image quality and positive prompt adherence. Our method also suppressed a generate-then-edit pipeline, while also having a much faster runtime. Code, ComfyUI node, and dataset are available in https://github.com/weathon/VSF/tree/main.

Primary Area: generative models

Submission Number: 5352