Papers › Taming Rectified Flow for Inversion and Editing

Taming Rectified Flow for Inversion and Editing

7 Nov 2024arXiv:2411.04746archive 2025-07-28

Jiangshan Wang, Junfu Pu, Zhongang Qi, Jiayi Guo, Yue Ma, Nisha Huang, Yuxin Chen, Xiu Li, Ying Shan

Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with inversion inaccuracies, which could further limit their effectiveness in downstream tasks such as image and video editing. To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow. Specifically, we derive the exact formulation of the rectified flow ODE and apply the high-order Taylor expansion to estimate its nonlinear components, significantly enhancing the precision of ODE solutions at each timestep. Building upon RF-Solver, we further propose RF-Edit, a general feature-sharing-based framework for image and video editing. By incorporating self-attention features from the inversion process into the editing process, RF-Edit effectively preserves the structural information of the source image or video while achieving high-quality editing results. Our approach is compatible with any pre-trained rectified-flow-based models for image and video tasks, requiring no additional training or optimization. Extensive experiments across generation, inversion, and editing tasks in both image and video modalities demonstrate the superiority and versatility of our method. The source code is available at https://github.com/wangjiangshan0725/RF-Solver-Edit.

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="2411.04746")

Code

Syntology Ran 2 of 10 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 10 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wangjiangshan0725/rf-solver-edit officialmentioned in papermentioned on GitHubpytorch 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

10 samples harvested; 2 ran; 0 honoured the contract we drafted; 8 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 · our draft was wrong
1ran · fixture could not drive it
8unverified

Licence: 10 of the 10 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 wangjiangshan0725/rf-solver-edit. “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.

get_lin_function wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/flux/sampling.py official repository ran · our draft was wrong no licence file found · pointer only · 3f6652da855a2ea0 · report
rope wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/flux/math.py official repository ran · fixture could not drive it no licence file found · pointer only · 17724d4203fa5863 · report
add_extra_models_args wangjiangshan0725/rf-solver-edit/Hunyuanvideo_Video_Edit/hyvideo/config.py official repository unverified no licence file found · pointer only · ec093a45a0d0f313 · report
add_network_args wangjiangshan0725/rf-solver-edit/Hunyuanvideo_Video_Edit/hyvideo/config.py official repository unverified no licence file found · pointer only · f36ad90936c64af9 · report
apply_rope wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/flux/math.py official repository unverified no licence file found · pointer only · 3444bbcc9065f707 · report
attention wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/flux/math.py official repository unverified no licence file found · pointer only · b17d74354ecaf7fe · report
encode wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/edit.py official repository unverified no licence file found · pointer only · 1498dfc442c71ecc · report
encode wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/gradio_demo.py official repository unverified no licence file found · pointer only · e02de920391fa756 · report
parse_args wangjiangshan0725/rf-solver-edit/Hunyuanvideo_Video_Edit/hyvideo/config.py official repository unverified no licence file found · pointer only · 7fd1cdc225d57a94 · report
time_shift wangjiangshan0725/rf-solver-edit/FLUX_Image_Edit/src/flux/sampling.py official repository unverified no licence file found · pointer only · 9f391f7c45a5bc94 · report

Tasks

Image GenerationText-to-Image GenerationVideo 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