对抗性扩散蒸馏
Adversarial Diffusion Distillation
AI总结：
本文提出对抗性扩散蒸馏（ADD），结合分数蒸馏与对抗损失，首次实现基础扩散模型在1-4步内的高质量实时图像合成，单步性能超越GAN和LCM，四步达到SDXL水平。
摘要：
我们提出了对抗性扩散蒸馏（Adversarial Diffusion Distillation，ADD），这是一种新颖的训练方法，能够在仅1-4个采样步骤内高效地采样大规模基础图像扩散模型，同时保持较高的图像质量。我们利用分数蒸馏，将大规模现成的图像扩散模型作为教师信号，并结合对抗损失，以确保即使在一步或两步采样的低步数条件下也能获得高图像保真度。我们的分析表明，我们的模型在单步采样中明显优于现有的少步方法（如GAN、Latent Consistency Models），并且仅需四步即可达到最先进扩散模型（SDXL）的性能。ADD是首个利用基础模型实现单步实时图像合成的方法。代码和权重可在 https://github.com/Stability-AI/generative-models 和 https://huggingface.co/stabilityai/ 获取。
英文摘要：
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. Our analyses show that our model clearly outperforms existing few-step methods (GANs, Latent Consistency Models) in a single step and reaches the performance of state-of-the-art diffusion models (SDXL) in only four steps. ADD is the first method to unlock single-step, real-time image synthesis with foundation models. Code and weights available under https://github.com/Stability-AI/generative-models and https://huggingface.co/stabilityai/ .
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。
