Conditional Image Generation with Score-Based Diffusion Models
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical analysis of different approaches to learning conditional probability distributions with score-based diffusion models. In particular, we prove results which provide a theoretical justification for one of the most successful estimators of the conditional score. Moreover, we introduce a multi-speed diffusion framework, which leads to a new estimator for the conditional score, performing on par with previous state-of-the-art approaches. Our theoretical and experimental findings are accompanied by an open source library MSDiff which allows for application and further research of multi-speed diffusion models.
Code (1)
Tasks
Conditional Image GenerationImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model
Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized…
Image GenerationTCFG: Tangential Damping Classifier-free Guidance
Diffusion models have achieved remarkable success in text-to-image synthesis, largely attributed to the use of classifier-free guidance (CFG), which enables high-quality, condition-aligned image generation. CFG combines …
Image GenerationImproving Diffusion-Based Generative Models via Approximated Optimal Transport
We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, …
Image GenerationAll are Worth Words: A ViT Backbone for Diffusion Models
Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architectu…
AllConditional Image GenerationImage GenerationText to Image Generation+1CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesis
In this paper, we propose a novel score-base generative model for unconditional raw audio synthesis. Our proposal builds upon the latest developments on diffusion process modeling with stochastic differential equations, …
Audio GenerationAudio SynthesisImage Generation