Papers › Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

1 Apr 2024CVPR 2024 1arXiv:2404.01050archive 2025-07-28

Haofeng Liu, Chenshu Xu, Yifei Yang, Lihua Zeng, Shengfeng He

Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion latent map in response to user inputs, causing global latent map alterations. This results in imprecise preservation of the original content and unsuccessful editing due to gradient vanishing. In contrast, we present DragNoise, offering robust and accelerated editing without retracing the latent map. The core rationale of DragNoise lies in utilizing the predicted noise output of each U-Net as a semantic editor. This approach is grounded in two critical observations: firstly, the bottleneck features of U-Net inherently possess semantically rich features ideal for interactive editing; secondly, high-level semantics, established early in the denoising process, show minimal variation in subsequent stages. Leveraging these insights, DragNoise edits diffusion semantics in a single denoising step and efficiently propagates these changes, ensuring stability and efficiency in diffusion editing. Comparative experiments reveal that DragNoise achieves superior control and semantic retention, reducing the optimization time by over 50% compared to DragDiffusion. Our codes are available at https://github.com/haofengl/DragNoise.

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 17 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 7 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: 17 samples from 1 repository, 12 ran (2 with no instrument failure; 10 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

haofengl/dragnoise officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 12 ran (10 instrument-failed) · 5 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

17 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 5 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.

1ran · violated contract
7ran · our draft was wrong
3ran; the contract check could not run
1ran
5unverified

Licence: 17 of the 17 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 haofengl/dragnoise. “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.

haofengl/dragnoise official repository 17 samples, 12 ran (10 instrument-failed) · 5 unverified
Fourier_filter in 6 papers utils/freeu_utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 63e5469c687a88a7 · report fixture: returned Tensor · level recorded 2026-09-22
check_handle_reach_target utils/drag_utils.py ran · our draft was wrong no licence file found · pointer only · a43f655fb03112d9 · report fixture: signature handle_points:list/1/Tensor, target_points:list/1/Tensor · returned Tensor · level recorded 2026-09-22
collate_fn in 500 papers lora/train_dreambooth_lora.py ran · our draft was wrong no licence file found · pointer only · 256040ccde7473f2 · report fixture: signature examples:list/1/dict, with_prior_preservation:bool/0/bool · returned dict · level recorded 2026-09-22
interpolate_feature_patch utils/drag_utils.py ran · our draft was wrong no licence file found · pointer only · 2cc475a39a00b385 · report fixture: signature feat:Tensor/4/float, y:Tensor/0/float, x:Tensor/0/float, r:int/0/int · returned Tensor · level recorded 2026-09-24
isinstance_str in 12 papers utils/freeu_utils.py ran · violated contract no licence file found · pointer only · cd5d5067de871c97 · report fixture: signature x:DerivedClass/0/?, cls_name:str/0/str · returned bool · level recorded 2026-09-22
mask_image in 9 papers drag_bench_evaluation/labeling_tool.py ran · our draft was wrong no licence file found · pointer only · ce0fe39e4583a703 · report fixture: signature image:ndarray/3/int, mask:ndarray/2/int, color:list/1/int, alpha:float/0/float · returned ndarray · level recorded 2026-09-26
override_attn_proc_forward utils/attn_utils.py ran · our draft was wrong no licence file found · pointer only · 5946ab6afcea0492 · report fixture: signature attn:callable/0/?, editor:callable/0/?, place_in_unet:str/0/str · returned function · level recorded 2026-09-24
override_lora_attn_proc_forward utils/attn_utils.py ran · our draft was wrong no licence file found · pointer only · 38ef74758ee24fab · report fixture: signature attn:callable/0/?, editor:callable/0/?, place_in_unet:str/0/str · returned function · level recorded 2026-09-24
point_tracking utils/drag_utils.py ran no licence file found · pointer only · dabd3d8b50d3828c · report fixture: signature F0:Tensor/4/float, F1:Tensor/4/float, handle_points:list/1/list, handle_points_init:list/1/list, args:Args/0/? · returned list · level recorded 2026-09-24
preprocess_image in 65 papers
census: 4 implementations from 6 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 3, kind float, dtype float32
drag_bench_evaluation/run_drag_diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · b6f9c54d3eaa1c8a · report fixture: signature image:ndarray/3/float, device:device/0/? · returned Tensor · level recorded, date not recorded
preprocess_image in 65 papers
census: 4 implementations from 6 papers, 2 distinct outputs on one shared input
drag_bench_evaluation/run_eval_similarity.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 45d032d395c815e4 · report fixture: signature image:ndarray/3/float, device:str/0/str · returned Tensor · level recorded 2026-09-26
store_img drag_bench_evaluation/labeling_tool.py ran · our draft was wrong no licence file found · pointer only · 09a03c76f61637c9 · report fixture: signature img:dict/0/?, length:int/0/int · returned tuple · level recorded 2026-09-26
import_model_class_from_model_name_or_path in 64 papers lora/train_dreambooth_lora.py unverified no licence file found · pointer only · 0eb3e94e8635150e · report
override_forward in 5 papers drag_pipeline.py unverified no licence file found · pointer only · 957e7cf270e3342a · report
parse_args in 355 papers lora/train_dreambooth_lora.py unverified no licence file found · pointer only · ce6abf8518e8fd67 · report
register_attention_editor_diffusers utils/attn_utils.py unverified no licence file found · pointer only · 486c3f3fef6e3481 · report
register_upblock2d utils/freeu_utils.py unverified no licence file found · pointer only · af1ac69dae95a5df · report

Tasks

Denoising

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Concatenated Skip ConnectionConvolutionDiffusionMax PoolingReLUU-Net

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