快速高分辨率图像合成：潜在对抗性扩散蒸馏
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
AI总结：
本文提出潜在对抗性扩散蒸馏（LADD），利用预训练潜在扩散模型特征，简化训练并提升性能，应用于Stable Diffusion 3（8B）得到SD3-Turbo，仅需四步采样即可匹配最先进文本到图像生成器性能，并验证其在图像编辑和修复中的有效性。
摘要：
扩散模型是图像和视频合成领域进步的主要驱动力，但存在推理速度慢的问题。蒸馏方法，如最近引入的对抗性扩散蒸馏（ADD），旨在将模型从多步推理转变为单步推理，但因其依赖固定的预训练DINOv2判别器，导致优化过程昂贵且困难。我们引入了潜在对抗性扩散蒸馏（LADD），一种新颖的蒸馏方法，克服了ADD的局限性。与基于像素的ADD不同，LADD利用预训练潜在扩散模型的生成特征。这种方法简化了训练并提升了性能，实现了高分辨率、多宽高比的图像合成。我们将LADD应用于Stable Diffusion 3（8B）以获得SD3-Turbo，这是一个快速模型，仅使用四步无引导采样即可匹配最先进的文本到图像生成器的性能。此外，我们系统地研究了其扩展行为，并展示了LADD在图像编辑和修复等多种应用中的有效性。
英文摘要：
Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator. We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In contrast to pixel-based ADD, LADD utilizes generative features from pretrained latent diffusion models. This approach simplifies training and enhances performance, enabling high-resolution multi-aspect ratio image synthesis. We apply LADD to Stable Diffusion 3 (8B) to obtain SD3-Turbo, a fast model that matches the performance of state-of-the-art text-to-image generators using only four unguided sampling steps. Moreover, we systematically investigate its scaling behavior and demonstrate LADD's effectiveness in various applications such as image editing and inpainting.
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。
