paper-with-me

Papers

Adversarial Diffusion Distillation

2023-11-28 · Axel Sauer, Dominik Lorenz, Andreas Blattmann, Robin Rombach

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/ .

📄 PDF Abstract BibTeX arXiv:2311.17042

Code (6)

stability-ai/generative-models 공식 구현 pytorch
NJU-PCALab/AddSR pytorch
ai-forever/kandinsky-3 pytorch
cumulo-autumn/streamdiffusion pytorch
leffff/FlowModels pytorch
leffff/adversarial-diffusion-distillation pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation

2025-08-25 · Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo arxiv

A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this li…

Voice Conversion

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

2024-03-18 · Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann 외

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 shif…

Image Generation

Instant Adversarial Purification with Adversarial Consistency Distillation

2024-08-30 · CVPR 2025 1 · Chun Tong Lei, Hon Ming Yam, Zhongliang Guo, Chun Pong Lau

Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise. Although some diffusion-based purification me…

Adversarial Purificationimage-classificationImage Classification

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

2025-07-24 · Yanzuo Lu, Yuxi Ren, Xin Xia, Shanchuan Lin 외 arxiv

Distribution Matching Distillation (DMD) is a promising score distillation technique that compresses pre-trained teacher diffusion models into efficient one-step or multi-step student generators. Nevertheless, its relian…

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

2024-02-21 · Shanchuan Lin, Anran Wang, Xiao Yang

We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive and adversarial distillation to achieve a …

Image GenerationText to Image GenerationText-to-Image Generation