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

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

29 May 2022arXiv:2205.15868archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thudm/cogvideo officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Text-to-Video GenerationVideo Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Generation UCF-101 CogVideo (128x128, class-conditional) FVD16 305 #22 of 48 Archive leaderboard report
Video Generation UCF-101 CogVideo (128x128, class-conditional) Inception Score 51.11 #22 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections