Adversarial Diffusion Distillation
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/ .
Code (6)
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
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 ConversionFast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
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 GenerationInstant Adversarial Purification with Adversarial Consistency Distillation
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 ClassificationAdversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
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
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