Related papers: PipeDiT: Accelerating Diffusion Transformers in Vi…

Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

With the increasing scale of models, the need for efficient distributed training has become increasingly urgent. Recently, many synchronous pipeline parallelism approaches have been proposed to improve training throughput. However, these…

Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans. More-recent Diffusion Transformers (DiTs) -- despite making significant headway in this context -- have only…

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…

Diffusion models have emerged as dominant performers for image generation. To support training large diffusion models, this paper studies pipeline parallel training of diffusion models and proposes DiffusionPipe, a synchronous pipeline…

In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of…

Video diffusion transformers (vDiTs) have made tremendous progress in text-to-video generation, but their high compute demands pose a major challenge for practical deployment. While studies propose acceleration methods to reduce workload at…

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

Diffusion models have achieved remarkable success in video generation; however, the high computational cost of the denoising process remains a major bottleneck. Existing approaches have shown promise in reducing the number of diffusion…

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…

We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with the given text descriptions. Due to a novel and efficient 3D…

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different…

Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is challenging due to their high computational cost, particularly at…

PipeDream is a Deep Neural Network(DNN) training system for GPUs that parallelizes computation by pipelining execution across multiple machines. Its pipeline parallel computing model avoids the slowdowns faced by data-parallel training when…

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…