通过显式条件实现无引导的图像编辑
Guidance Free Image Editing via Explicit Conditioning
AI总结：
针对条件扩散模型中无分类器引导（CFG）计算成本高的问题，提出显式条件调节（EC）技术，通过对噪声建模引导扩散过程，在图像编辑任务中以更低计算量实现更优的多样化高质量图像生成效果。
摘要：
当前条件扩散模型的采样机制主要依赖无分类器引导（CFG）来生成高质量图像。然而，CFG在每个时间步需要多次去噪过程，例如在图像编辑任务中最多需要三次过程，导致计算成本过高。本文提出一种新颖的条件调节技术，以减轻成熟引导技术的计算负担，从而显著提升扩散模型的推理速度。为此，我们提出了噪声分布基于输入模态的显式条件调节（EC）方法。直观而言，我们对噪声进行建模，以在扩散过程中引导条件扩散模型。我们在图像编辑任务上开展了评估，结果表明EC在生成多样化高质量图像方面优于CFG，且计算量显著降低。
英文摘要：
Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image editing tasks, resulting in excessive computational costs. This paper introduces a novel conditioning technique to ease the computational burden of the well-established guidance techniques, thereby significantly improving the inference time of diffusion models. We present Explicit Conditioning (EC) of the noise distribution on the input modalities to achieve this. Intuitively, we model the noise to guide the conditional diffusion model during the diffusion process. We present evaluations on image editing tasks and demonstrate that EC outperforms CFG in generating diverse high-quality images with significantly reduced computations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
