Papers › LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

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

26 Sep 2023arXiv:2309.15103archive 2025-07-28

Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of visually realistic and temporally coherent videos while b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: 1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. 2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2309.15103")

Code

Syntology Ran 1 of 2 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Vchitect/LaVie officialmentioned on GitHubpytorch report
arthur-qiu/freenoise-lavie mentioned 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

2 samples harvested; 1 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
1unverified

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Vchitect/LaVie. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

auto_inpainting Vchitect/LaVie/interpolation/sample.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 1d2865ffcf9f4a2b · report
auto_inpainting_copy_no_mask Vchitect/LaVie/interpolation/sample.py official repository unverified Apache-2.0 (permissive) · 0d01dfed98ff329d · report

Tasks

Super-ResolutionText-to-Video GenerationVideo GenerationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset Lavie Motion Quality 57.99 #4 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset Lavie Temporal Consistency 54.23 #4 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset Lavie Text-to-Video Alignment 68.49 #4 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset Lavie Total Score 234 #4 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset Lavie Visual Quality 52.83 #4 of 5 Archive leaderboard report
Text-to-Video Generation UCF-101 LAVIE (Zero-shot, 320x512) FVD16 526.30 #8 of 10 Archive leaderboard report
Video Generation UCF-101 LAVIE (320x512, text-conditional) FVD16 526.30 #37 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

BASEDiffusion

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