Related papers: Wan: Open and Advanced Large-Scale Video Generativ…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight…
We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the…
Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and…
We introduce the Seismic Waveforms dataset for Automatic Neural-network processing (SWAN), a comprehensive and standardized benchmark designed to advance data-driven seismic signal processing. SWAN aggregates diverse synthetic and real…
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)…
Video generation has increasingly gained interest in both academia and industry. Although commercial tools can generate plausible videos, there is a limited number of open-source models available for researchers and engineers. In this work,…
Generative AI is reshaping the media landscape, enabling unprecedented capabilities in video creation, personalization, and scalability. This paper presents a comprehensive SWOT analysis of Metas Movie Gen, a cutting-edge generative AI…
Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigate the scalability of Generative Adversarial Networks (GANs) through two design choices that have…
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity…
Large-scale 3D generative models require substantial computational resources yet often fall short in capturing fine details and complex geometries at high resolutions. We attribute this limitation to the inefficiency of current…
Recent unified models have made unprecedented progress in both understanding and generation. However, while most of them accept multi-modal inputs, they typically produce only single-modality outputs. This challenge of producing interleaved…
The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. However, a critical gap still remains between the theoretical…
The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs). These…
The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and…
We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or…
This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animation. Specifically, to preserve the robust generative…
Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains…
With the explosive growth of video data, video summarization, which attempts to seek the minimum subset of frames while still conveying the main story, has become one of the hottest topics. Nowadays, substantial achievements have been made…
We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidelity of image or video generative models. State-of-the-art 3D…