SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.02187 · CVPR · 2025

h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform

Kien Do, Thin Nguyen, Duc Kieu, Toan Nguyen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2503.02187.json · badge: /api/ran/2503.02187.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
nktoan/h-edit canonical (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
image2latent Ran
ran on a synthesized input
nktoan/h-edit/text-guided/main_masactrl.py
code served (permissive licence) · get_code("5aa5af5e51a36b65")
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 4, dtype family float, shape (2, 4, 2, 2) 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
import torch.nn as nn
import numpy as np
from PIL import Image

torch.manual_seed(0)

# Create a minimal VAE mock that has the encode method
class LatentDist(nn.Module):
    def __init__(self):
        super().__init__()
    
    def forward(self):
        pass

class VAE(nn.Module):
    def __init__(self):
        super().__init__()
    
    def encode(self, image):
        # Return a dict with 'latent_dist' containing a 'mean' tensor
        # Input image shape: (batch, 3, height, width) = (2, 3, 4, 5)
        # Latent should be smaller, e.g., (batch, 4, 2, 2)
        mean = torch.randn(2, 4, 2, 2)
        return {'latent_dist': type('obj', (object,), {'mean': mean})()}

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.vae = VAE()

# Create model instance
model = Model()

# Create a small test image as PIL Image
image_array = np.random.randint(0, 256, (4, 5, 3), dtype=np.uint8)
image = Image.fromarray(image_array)

# Device (CPU only)
device = 'cpu'

ARGS = {
    'model': model,
    'image': image,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 2, 2) — shape (2, 4, 2, 2) 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
h_Edit_R Not yet run
unverified (harvested, no recorded run)
nktoan/h-edit/face-swapping/inversion/h_edit_R.py
code served (permissive licence) · get_code("7bfeb47dfe8f7646")
How it ran

no invocation recorded.

load_image Not yet run
unverified (harvested, no recorded run)
nktoan/h-edit/text-guided/main_masactrl.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cure-lab/directinversion, is pointer only (licence: NONE) · get_code("79d9960693d3111d")
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 cure-lab/directinversion, 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. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
load_image 1 other paper
1 dated earlier
2310.01506 (2023-10)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code

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. Qualitative comparison between h-Edit and other training-free editing baselines. Our method achieves more accurate and faithful edits than the baselines. Additional visualizations are provided in the Appendix.

For agents

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

get_harvested_code_for_paper("2503.02187")
get_code_for_paper("2503.02187")
have("2503.02187")

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

curl https://syntology.ai/api/ran/2503.02187.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.02187.svg)](https://syntology.ai/paper/2503.02187)

Connect an agent — have() is free.