Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
By Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann, Patrick Esser, Robin Rombach. ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, 2024
299 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/f6ab25605dc36db5e4b4f2f167d905944d5203c4
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ming-Hsuan Yang
- Luc Van Gool
- Xiaogang Wang
- Jitendra Malik
- Trevor Darrell
- Dacheng Tao
- Andrew Zisserman
- Antonio Torralba
Citations in the corpus
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion (2025, unknown): “We use the 14B base model to generate 70k videos as the dataset for training GANs [70] Evaluation metrics.”
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (2025, unknown): “The advent of large-scale generative models has changed this landscape, enabling purely text-driven image synthesis and modifications that were previously impractical or impossible [11, 17, 41, 42, 40, 2, 12, 49, 21].”
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability (2024, unknown): “Potential solutions may include faster sampling techniques [89, 146] and training-based distillations [91, 93, 101, 103, 110, 124].”
- Improved Distribution Matching Distillation for Fast Image Synthesis (2024, methodology): “For this evaluation, we use the LADD [24] subset of PartiPrompts [69].”