Related papers: SDXL-Lightning: Progressive Adversarial Diffusion …

We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to accessible consumer devices. Our approach distills computationally prohibitive rectified flow models through a reformulated…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Recent advances in deep neural networks (DNNs) have led to remarkable success across a wide range of tasks. However, their susceptibility to adversarial perturbations remains a critical vulnerability. Existing diffusion-based adversarial…

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Recently, diffusion distillation methods have compressed thousand-step teacher diffusion models into one-step student generators while preserving sample quality. Most existing approaches train the student model using a diffusive divergence…

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models…

Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a…

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…

Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.…

Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature…

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…

This paper aims to apply a new deep learning approach to the task of generating raw audio files. It is based on diffusion models, a recent type of deep generative model. This new type of method has recently shown outstanding results with…

The rapid evolution of the fashion industry increasingly intersects with technological advancements, particularly through the integration of generative AI. This study introduces a novel generative pipeline designed to transform the fashion…

Diffusion Models (DMs) have achieved great success in image generation and other fields. By fine sampling through the trajectory defined by the SDE/ODE solver based on a well-trained score model, DMs can generate remarkable high-quality…

Synthetic Aperture Radar (SAR) provides all-weather, high-resolution imaging capabilities, but its unique imaging mechanism often requires expert interpretation, limiting its widespread applicability. Translating SAR images into more easily…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation…

In this paper, we propose a novel framework for solving high-definition video inverse problems using latent image diffusion models. Building on recent advancements in spatio-temporal optimization for video inverse problems using image…

Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this paper, we approach the dataset distillation problem from a…

Handwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion…