Related papers: RoPECraft: Training-Free Motion Transfer with Traj…
We present RopeTP, a novel framework that combines Robust pose estimation with a diffusion Trajectory Prior to reconstruct global human motion from videos. At the heart of RopeTP is a hierarchical attention mechanism that significantly…
Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of…
Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by…
Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with…
Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image…
Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim…
Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism…
Recently, diffusion models like StableDiffusion have achieved impressive image generation results. However, the generation process of such diffusion models is uncontrollable, which makes it hard to generate videos with continuous and…
The integration of Rotary Position Embedding (RoPE) in Multimodal Diffusion Transformer (MMDiT) has significantly enhanced text-to-image generation quality. However, the fundamental reliance of self-attention layers on positional embedding…
Recent advancements in diffusion-based models have demonstrated significant success in generating images from text. However, video editing models have not yet reached the same level of visual quality and user control. To address this, we…
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…
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…
In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that…
Diffusion models have emerged as a powerful paradigm for generative tasks such as image synthesis and video generation, with Transformer architectures further enhancing performance. However, the high computational cost of diffusion…
The transformer architecture has been widely applied to many machine learning tasks. A main bottleneck in the time to perform transformer computations is a task called attention computation. [Alman and Song, NeurIPS 2023] have shown that in…
This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales,…
Resolution generalization in image generation tasks enables the production of higher-resolution images with lower training resolution overhead. However, a key obstacle for diffusion transformers in addressing this problem is the mismatch…
Whole-body multimodal motion generation, controlled by text, speech, or music, has numerous applications including video generation and character animation. However, employing a unified model to achieve various generation tasks with…
First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of…
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain in these fields for generating diverse motions given past…