Papers › VidToMe: Video Token Merging for Zero-Shot Video Editing

VidToMe: Video Token Merging for Zero-Shot Video Editing

17 Dec 2023CVPR 2024 1arXiv:2312.10656archive 2025-07-28

Xirui Li, Chao Ma, Xiaokang Yang, Ming-Hsuan Yang

Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by utilizing pre-trained image diffusion models to translate source videos into new ones. Nevertheless, existing methods struggle to maintain strict temporal consistency and efficient memory consumption. In this work, we propose a novel approach to enhance temporal consistency in generated videos by merging self-attention tokens across frames. By aligning and compressing temporally redundant tokens across frames, our method improves temporal coherence and reduces memory consumption in self-attention computations. The merging strategy matches and aligns tokens according to the temporal correspondence between frames, facilitating natural temporal consistency in generated video frames. To manage the complexity of video processing, we divide videos into chunks and develop intra-chunk local token merging and inter-chunk global token merging, ensuring both short-term video continuity and long-term content consistency. Our video editing approach seamlessly extends the advancements in image editing to video editing, rendering favorable results in temporal consistency over state-of-the-art methods.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lixirui142/VidToMe officialmentioned on GitHubpytorchMITSyntology: 16 samples, 12 ran (5 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
3ran
4unverified

Licence: 0 of the 16 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 lixirui142/VidToMe. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lixirui142/VidToMe official repository 16 samples, 12 ran (5 instrument-failed) · 4 unverified
bipartite_soft_matching_randframe vidtome/merge.py ran MIT (permissive) · 66c921d24bbf4a88 · report fixture: signature metric:Tensor/3/float, F:int/0/int, ratio:float/0/float, unm_pre:int/0/int, generator:Generator/0/?, target_stride:int/0/int, align_batch:bool/0/bool, merge_mode:str/0/str · returned tuple · level recorded 2026-09-24
do_nothing in 25 papers
census: 6 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vidtome/merge.py ran · honoured contract fingerprinted MIT (permissive) · bd041cf95d856b5d · report fixture: signature x:Tensor/2/float, mode:NoneType/0/? · returned Tensor · level recorded 2026-09-22
init_generator in 5 papers vidtome/utils.py ran · our draft was wrong MIT (permissive) · 5b667bce9438efa5 · report fixture: signature device:device/0/?, fallback:Generator/0/? · returned Generator · level recorded 2026-09-24
ip2p_prepreocess utils/controlnet_utils.py ran · violated contract fingerprinted MIT (permissive) · 517ed2f5e48e4506 · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-24
isinstance_str in 12 papers vidtome/utils.py ran · violated contract MIT (permissive) · cd5d5067de871c97 · report fixture: signature x:DerivedClass/0/?, cls_name:str/0/str · returned bool · level recorded 2026-09-22
join_frame vidtome/utils.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 12347b72e892db7f · report fixture: signature x:Tensor/3/float, fsize:int/0/int · returned Tensor · level recorded 2026-09-24
load_config in 389 papers utils/config_utils.py ran · our draft was wrong MIT (permissive) · 81e5978bbc052c2b · report fixture: signature print_config:bool/0/bool · returned DictConfig · level recorded 2026-09-24
load_image in 273 papers utils/utils.py ran · honoured contract MIT (permissive) · 08704c5df640348e · report fixture: signature image_path:str/0/str · returned Tensor · level recorded 2026-09-24
make_diffusers_tome_block vidtome/patch.py ran · our draft was wrong MIT (permissive) · e4a3b96bb406cafa · report fixture: signature block_class:callable/0/? · returned type · level recorded 2026-09-24
mps_gather_workaround in 6 papers vidtome/merge.py ran · our draft was wrong MIT (permissive) · 16eb26a585c085e1 · report fixture: signature input:Tensor/3/float, dim:int/0/int, index:Tensor/3/int · returned Tensor · level recorded 2026-09-22
process_frames utils/utils.py ran MIT (permissive) · a7a7bcc32acb5c29 · report fixture: signature frames:Tensor/3/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-24
tile_preprocess utils/controlnet_utils.py ran MIT (permissive) · 944a3cb6dbaef645 · report fixture: signature image:Tensor/4/float, resample_rate:float/0/float, kwargs:dict/0/? · returned Tensor · level recorded 2026-09-24
compute_merge vidtome/patch.py unverified MIT (permissive) · bbc5db4d6781ec3d · report
make_tome_block vidtome/patch.py unverified MIT (permissive) · 6d0482841fa4703b · report
register_attention_control in 9 papers utils/pnp_utils.py unverified MIT (permissive) · 1a0f6cae08d3d7af · report
register_conv_control utils/pnp_utils.py unverified MIT (permissive) · 4700b1ebfdc72fef · report

Tasks

Video EditingVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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