Papers › Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using...

Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices

20 May 2024arXiv:2405.12211archive 2025-07-28

Nathaniel Cohen, Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli

Text-to-image (T2I) diffusion models achieve state-of-the-art results in image synthesis and editing. However, leveraging such pretrained models for video editing is considered a major challenge. Many existing works attempt to enforce temporal consistency in the edited video through explicit correspondence mechanisms, either in pixel space or between deep features. These methods, however, struggle with strong nonrigid motion. In this paper, we introduce a fundamentally different approach, which is based on the observation that spatiotemporal slices of natural videos exhibit similar characteristics to natural images. Thus, the same T2I diffusion model that is normally used only as a prior on video frames, can also serve as a strong prior for enhancing temporal consistency by applying it on spatiotemporal slices. Based on this observation, we present Slicedit, a method for text-based video editing that utilizes a pretrained T2I diffusion model to process both spatial and spatiotemporal slices. Our method generates videos that retain the structure and motion of the original video while adhering to the target text. Through extensive experiments, we demonstrate Slicedit's ability to edit a wide range of real-world videos, confirming its clear advantages compared to existing competing methods. Webpage: https://matankleiner.github.io/slicedit/

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Slicedit, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Slicedit') (how to connect); the free check have('2405.12211') needs no token.

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

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 9 ran (3 with no instrument failure; 6 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

fallenshock/Slicedit officialmentioned on GitHubpytorchSyntology: 20 samples, 9 ran (6 instrument-failed) · 11 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

20 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
3ran; the contract check could not run
11unverified

Licence: 0 of the 20 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 fallenshock/Slicedit. “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.

fallenshock/Slicedit official repository 20 samples, 9 ran (6 instrument-failed) · 11 unverified
add_margin in 9 papers Slicedit/inversion_utils.py ran · our draft was wrong MIT (permissive) · 25ab067e0902f41f · report fixture: signature pil_img:Image/0/?, top:int/0/int, right:int/0/int, bottom:int/0/int, left:int/0/int, color:tuple/1/int · returned Image · level recorded 2026-09-22
calc_mu Slicedit/inversion_utils.py ran · our draft was wrong MIT (permissive) · 0bd3fc32cad6ecc6 · report fixture: signature model:callable/0/?, model_output:Tensor/2/float, timestep:int/0/int, sample:Tensor/2/float, eta:float/0/float · returned tuple · level recorded 2026-09-22
encode_text in 11 papers Slicedit/inversion_utils.py ran · honoured contract MIT (permissive) · f10ef55e8b711ad5 · report fixture: signature model:callable/0/?, prompts:list/1/str · returned Tensor · level recorded 2026-09-22
get_variance Slicedit/inversion_utils.py ran · honoured contract MIT (permissive) · 48bf1963eb295892 · report fixture: signature model:callable/0/?, timestep:int/0/int · returned Tensor · level recorded 2026-09-22
isinstance_str in 12 papers Slicedit/inversion_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
prepare_extended_QKV Slicedit/inversion_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · f5482a07e744dbc9 · report fixture: signature self:callable/0/?, token_mat:Tensor/3/float, n_keyframes:int/0/int, n_orig_frames:int/0/int, sequence_length:int/0/int, h:int/0/int, dim:int/0/int, is_SA:bool/0/bool · returned Tensor · level recorded 2026-09-22
temporal_denoise Slicedit/inversion_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · f34768f578b617db · report fixture: signature model:callable/0/?, xt:Tensor/4/float, t:Tensor/0/int, neg_embedding:Tensor/3/float, text_embeddings_time:Tensor/3/float, st_batch_size:int/0/int, cfg_scale:float/0/float · returned Tensor · level recorded 2026-09-22
temporal_volume_denoise Slicedit/inversion_utils.py ran · our draft was wrong MIT (permissive) · b4c7235ec863b3ec · report fixture: signature model:callable/0/?, n_frames:int/0/int, volume_t:Tensor/5/float, t:Tensor/0/int, negative_time_embedding:Tensor/3/float, text_embeddings_time:Tensor/3/float, st_batch_size:int/0/int, cfg_scale_time:float/0/float, x_and_y:bool/0/bool · returned Tensor · level recorded 2026-09-22
tensor_to_pil in 16 papers Slicedit/inversion_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 6fd0be0931229e05 · report fixture: signature tensor_imgs:Tensor/4/float · returned list · level recorded 2026-09-22
create_video_from_frames Slicedit/inversion_utils.py unverified MIT (permissive) · 7a3671581feafc24 · report
image_grid in 41 papers Slicedit/inversion_utils.py unverified MIT (permissive) · 7be3c3d9f3cc6b46 · report
pred_noise_xy_func Slicedit/inversion_utils.py unverified MIT (permissive) · 2ae8041181b7a137 · report
register_conv_injection Slicedit/inversion_utils.py unverified MIT (permissive) · fca1391a5cb280dd · report
register_denoiser_xy Slicedit/inversion_utils.py unverified MIT (permissive) · 23e4bdeddbc7c01c · report
register_extended_attention Slicedit/inversion_utils.py unverified MIT (permissive) · b4506ee67589b117 · report
register_n_keyframes Slicedit/inversion_utils.py unverified MIT (permissive) · 5211e19ad1d3f310 · report
register_time Slicedit/inversion_utils.py unverified MIT (permissive) · 712a553bf52ae1a4 · report
sample_xts_from_x0_and_eps Slicedit/inversion_utils.py unverified MIT (permissive) · a7822d3351721ee9 · report
save_video in 6 papers Slicedit/inversion_utils.py unverified MIT (permissive) · dccfdcbb40353e0b · report
slicedit_ddpm_inversion_loop Slicedit/inversion_utils.py unverified MIT (permissive) · 32b283bd397c92d0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Slicedit (graph method: Slicedit), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. ddim_inversion_step entry · level 2 · ran · 6c2dabb00c1cdf29012e644628de5af6dde08181d9d99eba1e28fc86cfe6b429

harvested Assembly for Slicedit (graph method: Slicedit). 20 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. slicedit_ddpm_inversion_loop entry · level 0 · unverified · 32b283bd397c92d0
  2. calc_mu scheduler · level 1 · ran · our draft was wrong · 0bd3fc32cad6ecc6
  3. create_video_from_frames helper · level 0 · unverified · 7a3671581feafc24
  4. encode_text data_transform · level 1 · ran · honoured contract · f10ef55e8b711ad5
  5. image_grid helper · level 0 · unverified · 7be3c3d9f3cc6b46
  6. pred_noise_xy_func sampler · level 0 · unverified · 2ae8041181b7a137
  7. register_conv_injection model · level 0 · unverified · fca1391a5cb280dd
  8. register_extended_attention model · level 0 · unverified · b4506ee67589b117
  9. register_n_keyframes helper · level 0 · unverified · 5211e19ad1d3f310
  10. sample_xts_from_x0_and_eps helper · level 0 · unverified · a7822d3351721ee9
  11. save_video helper · level 0 · unverified · dccfdcbb40353e0b
  12. temporal_volume_denoise sampler · level 1 · ran · our draft was wrong · b4c7235ec863b3ec
  13. get_variance scheduler · level 1 · ran · honoured contract · 48bf1963eb295892
  14. add_margin helper · level 1 · ran · our draft was wrong · 25ab067e0902f41f
  15. tensor_to_pil helper · level 1 · ran; the contract check could not run (RAISES) · 6fd0be0931229e05
  16. register_denoiser_xy helper · level 0 · unverified · 23e4bdeddbc7c01c
  17. register_time helper · level 0 · unverified · 712a553bf52ae1a4
  18. isinstance_str helper · level 1 · ran · violated contract · cd5d5067de871c97
  19. prepare_extended_QKV helper · level 1 · ran; the contract check could not run (RAISES) · f5482a07e744dbc9
  20. temporal_denoise sampler · level 1 · ran; the contract check could not run (RAISES) · f34768f578b617db

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.12211") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationVideo Editing

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