Papers › VideoComposer: Compositional Video Synthesis with Motion Controllability

VideoComposer: Compositional Video Synthesis with Motion Controllability

3 Jun 2023NeurIPS 2023 11arXiv:2306.02018archive 2025-07-28

Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, Jingren Zhou

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we introduce the motion vector from compressed videos as an explicit control signal to provide guidance regarding temporal dynamics. In addition, we develop a Spatio-Temporal Condition encoder (STC-encoder) that serves as a unified interface to effectively incorporate the spatial and temporal relations of sequential inputs, with which the model could make better use of temporal conditions and hence achieve higher inter-frame consistency. Extensive experimental results suggest that VideoComposer is able to control the spatial and temporal patterns simultaneously within a synthesized video in various forms, such as text description, sketch sequence, reference video, or even simply hand-crafted motions. The code and models will be publicly available at https://videocomposer.github.io.

PaperPDFConference PDFCodeCode 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="2306.02018")

Code

Syntology Ran 5 of 21 code samples harvested from 2 repositories linked to this paper; 16 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 20 samples from 2 repositories, 4 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ali-vilab/videocomposer mentioned on GitHubpytorch report
damo-vilab/videocomposer mentioned on GitHubpytorchMIT report
mindspore-lab/mindone mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready 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

21 samples harvested; 5 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
1ran · fixture could not drive it
1ran
16unverified

Licence: 1 of the 21 samples is 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

interpolate_fn damo-vilab/videocomposer/artist/ops/dpm_solver.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 6a35b62fbc80f70a · report
Normalize ali-vilab/videocomposer/tools/videocomposer/autoencoder.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report
model_wrapper damo-vilab/videocomposer/artist/ops/dpm_solver.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 0e68c8747f1cfcd9 · report
uint2single damo-vilab/videocomposer/artist/ops/degration.py community (archive-listed) ran fingerprinted MIT (permissive) · 9aa26711dc747d66 · report
all_gather damo-vilab/videocomposer/utils/distributed.py community (archive-listed) unverified MIT (permissive) · a1ba6b0c4d96716f · report
all_reduce damo-vilab/videocomposer/utils/distributed.py community (archive-listed) unverified MIT (permissive) · 439067335e7b67b5 · report
beta_schedule damo-vilab/videocomposer/artist/ops/diffusion.py community (archive-listed) unverified MIT (permissive) · 6310b674ca6c549f · report
discretized_gaussian_log_likelihood damo-vilab/videocomposer/artist/ops/losses.py community (archive-listed) unverified MIT (permissive) · c0132499fc4c9979 · report
get_logger damo-vilab/videocomposer/utils/logging.py community (archive-listed) unverified MIT (permissive) · b6d6bcb982b768cc · report
get_rank damo-vilab/videocomposer/artist/ops/distributed.py community (archive-listed) unverified MIT (permissive) · 1d504697143a06b9 · report
get_world_size damo-vilab/videocomposer/artist/ops/distributed.py community (archive-listed) unverified MIT (permissive) · 151fc386a67a4f69 · report
imread_uint damo-vilab/videocomposer/artist/ops/degration.py community (archive-listed) unverified MIT (permissive) · 57ba5b9dc5dfa8d3 · report
is_master_proc damo-vilab/videocomposer/utils/distributed.py community (archive-listed) unverified MIT (permissive) · 30fda522caa99e6e · report
kl_divergence damo-vilab/videocomposer/artist/ops/losses.py community (archive-listed) unverified MIT (permissive) · 24f8868cf6825433 · report
midas_v3 damo-vilab/videocomposer/artist/models/midas.py community (archive-listed) unverified MIT (permissive) · 75297920dd4b445d · report
model_wrapper_guided_diffusion damo-vilab/videocomposer/artist/ops/dpm_solver.py community (archive-listed) unverified MIT (permissive) · c877d9da577fc0d3 · report
new_group damo-vilab/videocomposer/artist/ops/distributed.py community (archive-listed) unverified MIT (permissive) · 69723155a0580292 · report
random_resize damo-vilab/videocomposer/gen_sketch.py community (archive-listed) unverified MIT (permissive) · 3194e97648f3e21e · report
single2uint damo-vilab/videocomposer/artist/ops/degration.py community (archive-listed) unverified MIT (permissive) · 83caf98edcef2e94 · report
standard_normal_cdf damo-vilab/videocomposer/artist/ops/losses.py community (archive-listed) unverified MIT (permissive) · 59f8d2f892f3195a · report
nonlinearity identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 3137073275f8c21a · report

Tasks

Image GenerationText-to-Video Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset ModelScope Motion Quality 53.09 #5 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset ModelScope Temporal Consistency 54.46 #5 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset ModelScope Text-to-Video Alignment 57.8 #5 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset ModelScope Total Score 218 #5 of 5 Archive leaderboard report
Text-to-Video Generation EvalCrafter Text-to-Video (ECTV) Dataset ModelScope Visual Quality 52.47 #5 of 5 Archive leaderboard report
Text-to-Video Generation MSR-VTT VideoComposer CLIPSIM 0.2932 #10 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT VideoComposer FVD 580 #10 of 18 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.

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