Related papers: CPA: Camera-pose-awareness Diffusion Transformer f…
In recent years, large-scale pre-trained diffusion transformer models have made significant progress in video generation. While current DiT models can produce high-definition, high-frame-rate, and highly diverse videos, there is a lack of…
Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In…
Generating photorealistic videos of digital humans in a controllable manner is crucial for a plethora of applications. Existing approaches either build on methods that employ template-based 3D representations or emerging video generation…
Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…
Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…
Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…
Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To reduce their substantial computational costs, feature caching techniques have been proposed to accelerate inference by…
We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into…
Since videos record objects moving coherently, adjacent video frames have commonness (similar object appearances) and uniqueness (slightly changed postures). To prevent redundant modeling of common video signals, we propose a novel…
Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high…
Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and…
Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative models such as Stable Diffusion can aid by generating…
Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, face, and clothing,…
Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints…
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its…
Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…
In this paper, we introduce a novel approach to trajectory generation for autonomous driving, combining the strengths of Diffusion models and Transformers. First, we use the historical trajectory data for efficient preprocessing and…
Multi-person interactive motion generation, a critical yet under-explored domain in computer character animation, poses significant challenges such as intricate modeling of inter-human interactions beyond individual motions and generating…
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation,…
Portrait animation aims to generate photo-realistic videos from a single source image by reenacting the expression and pose from a driving video. While early methods relied on 3D morphable models or feature warping techniques, they often…