AI Paper Atlas

Research map / Video / Video generation

LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Ceyuan Yang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu and 8 more

IJCV 2024 · Video › Video generation · approach: Compositional text-to-video diffusion · 439 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use joint image-video fine-tuning instead of fine-tuning the entire UNet on video only (ablation)LaVie base T2V · qualitative training scheme comparisonvisual quality / concept retentionImproved
use joint image-video fine-tuning instead of training only temporal modules (ablation)LaVie base T2V · qualitative training scheme comparisonvisual qualityImproved
train on WebVid10M+Vimeo25M and use class names as prompts, compared with Video LDMLaVie · UCF101 zero-shotFVD: 550.61 -> 526.30Improved
compare to Make-A-Video trained on larger HD-VILA-100M data with template promptsLaVie · UCF101 zero-shotFVD: 367.23 -> 526.30Hurt
compare to Make-A-Video on MSR-VTTLaVie · MSR-VTT zero-shotCLIPSIM: 0.3049 -> 0.2949Hurt
compare to Video LDM and ModelScope on MSR-VTTLaVie · MSR-VTT zero-shotCLIPSIM: 0.2929 -> 0.2949No clear effect
compare LaVie to ModelScope in human pairwise preferenceLaVie · human preference overall qualitypreference rate: 75.00%Improved
compare LaVie to ModelScope on motion smoothnessLaVie · human evaluationproportion good: 0.31 -> 0.35Improved
compare LaVie to ModelScope on background consistencyLaVie · human evaluationproportion good: 0.63 -> 0.72Improved
compare LaVie to ModelScope on face/body/hand qualityLaVie · human evaluationproportion good: 0.18 -> 0.24Improved

Later papers that compared with this method

14 later accepted papers report LaVie as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

6 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy