ReNeg: Learning Negative Embedding with Reward Guidance

Figure 1 . We develop ReNeg, a versatile negative embedding seamlessly adaptable to text-to-image and even text-to-video models. Strikingly simple yet highly effective, ReNeg amplifies the visual appeal of outputs from base Stable Diffusion (SD) models. '+N * ' and '+ReNeg' indicate improved results with handcrafted negative prompts and our negative embedding, respectively.