Related papers: Sparse VideoGen2: Accelerate Video Generation with…

Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study…

Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single-GPU inference becomes inefficient due to increased latency…

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity or fail to adapt to heterogeneous token distributions…

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Real-time video generation with Diffusion Transformers is bottlenecked by the quadratic cost of 3D self-attention, especially in real-time regimes that are both few-step and autoregressive, where errors compound across time and each…

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 Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…

Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse attention methods degrade under high sparsity. We show empirically that generation quality…

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally…

Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard inference applies the same number of denoising steps uniformly to every token in the sequence.…

Text-to-video generation enhances content creation but is highly computationally intensive: The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number of pixels. This makes minute-length video generation…

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…

Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or…

The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they…

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation…

Diffusion generative models have become the standard for producing high-quality, coherent video content, yet their slow inference speeds and high computational demands hinder practical deployment. Although both quantization and sparsity can…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…