SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02583 · CVPR · 2024

DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing

Jian Zhang, Ying Shan, Xintao Wang, Chong Mou, Jiechong Song

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.02583.json · badge: /api/ran/2402.02583.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mc-e/dragondiffusion canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
mc-e/dragondiffusion/src/unet/attention_processor.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rainbowluocs/openomni, is pointer only (licence: NONE) · get_code("5105747c2711b1cb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from rainbowluocs/openomni, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

fourier_filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mc-e/dragondiffusion/src/unet/unet_2d_blocks.py
code served (permissive licence) · get_code("dbca6d577684a526")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 5, dtype family float, shape (2, 4, 1, 8, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# x_in is indexed as x_in[:, :, 0], so it needs at least 3 dimensions
# Shape: (batch=2, channels=4, depth=1, height=8, width=8)
# After x = x_in[:, :, 0], shape becomes (2, 4, 8, 8)
x_in = torch.randn(2, 4, 1, 8, 8, dtype=torch.float32)

threshold = 2
scale = 1

ARGS = {
    "x_in": x_in,
    "threshold": threshold,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 5, dtype family float, shape (2, 4, 1, 8, 8) — shape (2, 4, 1, 8, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mc-e/dragondiffusion/src/unet/attention_processor.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Minyeol/MIDAS, is pointer only (licence: NONE) · get_code("4cb2e2a2ca0bec9f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Minyeol/MIDAS, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

show_point_or_box Ran
ran, violated the contract we drafted
mc-e/dragondiffusion/src/demo/utils.py
code served (permissive licence) · get_code("e68f1a4a85e1bf5a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (100, 100, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import cv2
import numpy as np

# Create a small test image (100x100 RGB image)
image = np.zeros((100, 100, 3), dtype=np.uint8)

# Test case 1: single point
global_points_single = [(50, 50)]

# Test case 2: two points (for rectangle)
global_points_two = [(20, 20), (80, 80)]

# We'll use the two-point case as it exercises more of the function
ARGS = {
    "image": image,
    "global_points": global_points_two
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (100, 100, 3) — shape (100, 100, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_down_block Not yet run
unverified (harvested, no recorded run)
mc-e/dragondiffusion/src/unet/unet_2d_blocks.py
code served (permissive licence) · get_code("7a72ef97f6c9b9ed")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
mc-e/dragondiffusion/src/unet/unet_2d_blocks.py
code served (permissive licence) · get_code("d72465b2267e2666")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
FeedForward 47 other papers
8 dated earlier, 1 the same month, 37 later, 1 same year, order not determinable · 4 only as an assembly brick
2204.14198 (2022-04)
Flamingo: a Visual Language Model for Few-Shot Learning
2308.02463 (2023-08)
Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
and 44 more not named here
reshape_tensor 30 other papers
4 dated earlier, 26 later
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
and 27 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. Our DiffEditor can perform various fine-grained image editing tasks. Given an image, users can select an object to move or resize. Or they can drag content with points. Moreover, users can choose a reference image for object pasting and appearance replacing.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.02583")
get_code_for_paper("2402.02583")
have("2402.02583")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.02583.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.02583.svg)](https://syntology.ai/paper/2402.02583)

Connect an agent — have() is free.