REVIEW 9 cited by
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 9 Pith papers
-
From Bit-Position Sensitivity to Unequal Error Protection for DNN Inference Memory
Per-bit fault injection on 16 DNNs yields safe-unprotected-bit floors (FP16:6, BF16:4, FP32:15) that power a selective-ECC codec with ~27.8% less ECC area and ~17% lower BF16 read energy.
-
ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
ShortFT fine-tunes Stable Diffusion by backpropagating reward gradients through a distilled few-step shortcut denoising chain, improving alignment scores over DRaFT-LV and DRTune.
-
Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
A new adversarial distribution matching loss for diffusion distillation gives one-step and few-step generators that match or exceed prior distillation methods on SDXL, SD3, and CogVideoX.
-
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
Fine-tuning a pretrained diffusion model with a GAN objective and most weights frozen yields a one-step generator that matches or beats prior distillation methods on several datasets.
-
SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
Phase-aware sampling cuts Stable Diffusion's compute by roughly 2.4x to 5.7x with only small CLIP-score changes, and the accompanying FPGA accelerator turns this into 2.7x to 6.0x energy savings over an Nvidia V100 GPU.
-
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
Normalized Attention Guidance (NAG) stabilizes attention-space extrapolation with L1 normalization and refinement, restoring negative prompting in few-step diffusion models across architectures and modalities.
-
Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution
DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...
-
Hidden Bias in the Machine: Stereotypes in Text-to-Image Models
Text-to-image models reproduce and amplify stereotypes about gender, race, age, and body type across a broad set of everyday prompt categories.
- How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
Discussion (0). Continue with ORCID to comment.