Related papers: You Only Sample Once: Taming One-Step Text-to-Imag…

Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains challenging, as existing methods consistently fail to…

Synthesis of high resolution images using Generative Adversarial Networks (GANs) is challenging, which usually requires numbers of high-end graphic cards with large memory and long time of training. In this paper, we propose a two-stage…

With the rapid development of AIGC technologies, generative image steganography has attracted increasing attention due to its high imperceptibility and flexibility. However, existing generative steganography methods often maintain…

We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this complex joint distribution, we adopt a factorized approach:…

Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads to a suboptimal trade-off between inference speed and…

The rapid advancement in image generation models has predominantly been driven by diffusion models, which have demonstrated unparalleled success in generating high-fidelity, diverse images from textual prompts. Despite their success,…

Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage…

One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with…

We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously…

Given a large dataset for training, generative adversarial networks (GANs) can achieve remarkable performance for the image synthesis task. However, training GANs in extremely low data regimes remains a challenge, as overfitting often…

Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step generator. While existing methods have made notable progress,…

Generating desired images conditioned on given text descriptions has received lots of attention. Recently, diffusion models and autoregressive models have demonstrated their outstanding expressivity and gradually replaced GAN as the favored…

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation is associated with synchronous denoising, where…

Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To achieve the personalization capability, existing methods rely…

The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated…

In this paper, we present the Directly Denoising Diffusion Model (DDDM): a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better performance. DDDMs require…

Although diffusion models exhibit impressive generative capabilities, existing methods for stylized image generation based on these models often require textual inversion or fine-tuning with style images, which is time-consuming and limits…

Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference steps. Previous efforts on fewer-step distillation attempt…

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial…

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive…