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 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="2312.10656")

Code

Syntology Ran 12 of 16 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lixirui142/VidToMe officialmentioned on GitHubpytorchMIT 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; 1 honoured the contract we drafted; 4 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
9ran
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. “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.

bipartite_soft_matching_randframe lixirui142/VidToMe/vidtome/merge.py official repository ran MIT (permissive) · 66c921d24bbf4a88 · report
do_nothing lixirui142/VidToMe/vidtome/merge.py official repository ran · honoured contract fingerprinted MIT (permissive) · bd041cf95d856b5d · report
init_generator lixirui142/VidToMe/vidtome/utils.py official repository ran MIT (permissive) · 5b667bce9438efa5 · report
ip2p_prepreocess lixirui142/VidToMe/utils/controlnet_utils.py official repository ran fingerprinted MIT (permissive) · 517ed2f5e48e4506 · report
isinstance_str lixirui142/VidToMe/vidtome/utils.py official repository ran · violated contract MIT (permissive) · cd5d5067de871c97 · report
join_frame lixirui142/VidToMe/vidtome/utils.py official repository ran fingerprinted MIT (permissive) · 12347b72e892db7f · report
load_config lixirui142/VidToMe/utils/config_utils.py official repository ran MIT (permissive) · 81e5978bbc052c2b · report
load_image lixirui142/VidToMe/utils/utils.py official repository ran MIT (permissive) · 08704c5df640348e · report
make_diffusers_tome_block lixirui142/VidToMe/vidtome/patch.py official repository ran MIT (permissive) · e4a3b96bb406cafa · report
mps_gather_workaround lixirui142/VidToMe/vidtome/merge.py official repository ran · our draft was wrong MIT (permissive) · 16eb26a585c085e1 · report
process_frames lixirui142/VidToMe/utils/utils.py official repository ran MIT (permissive) · a7a7bcc32acb5c29 · report
tile_preprocess lixirui142/VidToMe/utils/controlnet_utils.py official repository ran MIT (permissive) · 944a3cb6dbaef645 · report
compute_merge lixirui142/VidToMe/vidtome/patch.py official repository unverified MIT (permissive) · bbc5db4d6781ec3d · report
make_tome_block lixirui142/VidToMe/vidtome/patch.py official repository unverified MIT (permissive) · 6d0482841fa4703b · report
register_attention_control lixirui142/VidToMe/utils/pnp_utils.py official repository unverified MIT (permissive) · 1a0f6cae08d3d7af · report
register_conv_control lixirui142/VidToMe/utils/pnp_utils.py official repository 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