Related papers: SmoothCache: A Universal Inference Acceleration Te…

Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent…

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the…

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally…

Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and…

Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or…

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make…

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an…

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts:…

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and computational efficiency. As video length increases, issues such as visual degradation, portrait…

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…

Diffusion models have achieved remarkable success in text-to-speech (TTS), even in zero-shot scenarios. Recent efforts aim to address the trade-off between inference speed and sound quality, often considered the primary drawback of…

Diffusion model-based channel estimators have shown impressive performance but suffer from high computational complexity because they rely on iterative reverse sampling. This paper proposes a sampling-free diffusion transformer (DiT) for…

Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with various "add-on"…

The growing adoption of generative AI in real-world applications has exposed a critical bottleneck in the computational demands of diffusion-based text-to-image models. In this work, we propose KDC-Diff, a novel and scalable generative…

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…