Related papers: Progressive Autoregressive Video Diffusion Models
Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to…
Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive adversarial post-training (AAPT) to transform a pre-trained…
We propose a novel inference technique based on a pretrained diffusion model for text-conditional video generation. Our approach, called FIFO-Diffusion, is conceptually capable of generating infinitely long videos without additional…
Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended…
Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in…
Video frame transmission delay is critical in real-time applications such as online video gaming, live show, etc. The receiving deadline of a new frame must catch up with the frame rendering time. Otherwise, the system will buffer a while,…
Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, both abstractions…
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)…
Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…
Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and…
Video diffusion models have recently achieved remarkable results in video generation. Despite their encouraging performance, most of these models are mainly designed and trained for short video generation, leading to challenges in…
We present a method for generating Streetscapes-long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., city name, weather), as well as an underlying map/layout…
Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos. To address this, we propose a novel distributed inference strategy,…
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps…
Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by…
Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…
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…
Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…
Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…
Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the inability to synthesize long-duration…