Related papers: Less is Enough: Training-Free Video Diffusion Acce…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Despite recent progress in video generation, inference speed remains a major bottleneck. A common acceleration strategy involves reusing model outputs via caching mechanisms at fixed intervals. However, we find that such fixed-frequency…

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…

Diffusion Policy has demonstrated strong visuomotor modeling capabilities, but its high computational cost renders it impractical for real-time robotic control. Despite huge redundancy across repetitive denoising steps, existing diffusion…

Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling…

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model…

Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive…

Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex…

Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step…

This paper presents a method to accelerate the inference process of diffusion transformer (DiT)-based text-to-speech (TTS) models by applying a selective caching mechanism to transformer layers. Specifically, I integrate SmoothCache into…

Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video…

Video generation has made remarkable progress in recent years, especially since the advent of the video diffusion models. Many video generation models can produce plausible synthetic videos, e.g., Stable Video Diffusion (SVD). However, most…

Distilled video generation models offer fast and efficient synthesis but struggle with motion customization when guided by reference videos, especially under training-free settings. Existing training-free methods, originally designed for…

Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of…

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

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…

Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…

Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…

Recent advancements in Unet-based diffusion models, such as ControlNet and IP-Adapter, have introduced effective spatial and subject control mechanisms. However, the DiT (Diffusion Transformer) architecture still struggles with efficient…

Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate…