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.

通过利用预训练的潜在扩散模型的生成特征，我们引入了一种名为 LADD 的新的蒸馏方法，它简化了训练并提高了性能，实现了高分辨率的多纵横比图像合成。我们将 LADD 应用于 Stable Diffusion 3 (8B) 以获得 SD3-Turbo，这是一个快速模型，仅使用四个无导向采样步骤就能达到与现有技术文本到图像生成器相当的性能。此外，我们还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各种应用中的有效性。