We introduce Value Sign Flip (VSF), a simple and efficient method for incorporating negative prompt guidance in few-step diffusion and flow-matching image 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 small computational overhead and integrates effectively with MMDiT-style architectures such as Stable Diffusion 3.5 Turbo, as well as cross-attention-based models like Wan. We validate VSF on challenging datasets with complex prompt pairs and demonstrate superior performance in both static image and video generation tasks. Experimental results show that VSF significantly improves negative prompt adherence compared to prior methods in few-step models, and even CFG in non-few-step models, while maintaining competitive image quality. Code and ComfyUI node are available in https://github.com/weathon/VSF/tree/main.

翻译：我们提出了值符号翻转（VSF），这是一种在少步扩散和流匹配图像生成模型中融入负向提示引导的简单且高效的方法。与现有的方法如无分类器引导（CFG）、NASA和NAG不同，VSF通过翻转来自负向提示的注意力值的符号来动态抑制不需要的内容。我们的方法仅需很小的计算开销，并能有效地与MMDiT风格的架构（如Stable Diffusion 3.5 Turbo）以及基于交叉注意力的模型（如Wan）集成。我们在具有复杂提示对的数据集上验证了VSF，并展示了其在静态图像和视频生成任务中的优越性能。实验结果表明，在少步模型中，与先前方法相比，VSF显著提高了对负向提示的遵循度，甚至优于非少步模型中的CFG，同时保持了有竞争力的图像质量。代码和ComfyUI节点可在 https://github.com/weathon/VSF/tree/main 获取。