paper-with-me

Papers

CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

2022-05-29 · Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, Jie Tang

Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model understanding complex movement semantics. In this work, we present 9B-parameter transformer CogVideo, trained by inheriting a pretrained text-to-image model, CogView2. We also propose multi-frame-rate hierarchical training strategy to better align text and video clips. As (probably) the first open-source large-scale pretrained text-to-video model, CogVideo outperforms all publicly available models at a large margin in machine and human evaluations.

📄 PDF Abstract BibTeX arXiv:2205.15868

Code (1)

thudm/cogvideo 공식 구현 pytorch

Tasks

Text-to-Video GenerationVideo Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

2024-08-12 · Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding 외

We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 76…

Text-to-Video GenerationVideo AlignmentVideo CaptioningVideo Generation

VideoPhy: Evaluating Physical Commonsense for Video Generation

2024-06-05 · Hritik Bansal, Zongyu Lin, Tianyi Xie, Zeshun Zong 외

Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts, synthesize realistic mo…

Video Generation

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

2025-05-25 · Shenggan Cheng, Yuanxin Wei, Lansong Diao, Yong liu 외

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-…

Video EditingVideo Generation

BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation

2025-08-14 · Youping Gu, Xiaolong Li, Yuhao Hu, Minqi Chen 외 arxiv

Diffusion Transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottl…

Video Generation

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

2024-12-06 · Yibin Wang, Zhiyu Tan, Junyan Wang, Xiaomeng Yang 외

Recent advancements in text-to-video (T2V) generative models have shown impressive capabilities. However, these models are still inadequate in aligning synthesized videos with human preferences (e.g., accurately reflecti…