Related papers: ASGDiffusion: Parallel High-Resolution Generation …

Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions higher than those used during training. Although numerous…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge.…

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…

Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive…

Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks. Recent solutions for these tasks often…

Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices.…

Hyperspectral and multispectral image (HSI-MSI) fusion involves combining a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) to generate a high-resolution hyperspectral image (HR-HSI). Most…

This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth…

We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization…

Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…

Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This incompatibility precludes reusing robust AR priors,…

Single Image Super Resolution (SISR) is the task of producing a high resolution (HR) image from a given low-resolution (LR) image. It is a well researched problem with extensive commercial applications such as digital camera, video…

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex…

While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming data synchronizing between workers. To alleviate this…

The increasing complexity of deep learning recommendation models (DLRM) has led to a growing need for large-scale distributed systems that can efficiently train vast amounts of data. In DLRM, the sparse embedding table is a crucial…

High resolution (HR) 3D images are widely used nowadays, such as medical images like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). However, segmentation of these 3D images remains a challenge due to their high spatial…

Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency,…

Standard clothing asset generation involves restoring forward-facing flat-lay garment images displayed on a clear background by extracting clothing information from diverse real-world contexts, which presents significant challenges due to…

Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes. This issue primarily stems from the model being trained on pairs of…