SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12705 · 2024

IMAGDressing-v1: Customizable Virtual Dressing

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 0 have no contract verdict; 4 failures of our instrument; 0 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/2407.12705.json · badge: /api/ran/2407.12705.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
muzishen/imagdressing canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
muzishen/imagdressing/IGPair.py
code served (permissive licence) · get_code("315fe1f13ceb1ddd")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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)

# Create sample data that matches what collate_fn expects
data = [
    {
        'vae_person': torch.randn(2, 4),  # batch_size=2, feature_dim=4
        'vae_clothes': torch.randn(2, 4),
        'clip_image': torch.randn(3, 4),  # 3 images, 4 features
        'drop_image_embed': torch.randn(2, 4),
        'text': "a person wearing clothes",
        'text_input_ids': torch.randint(0, 100, (2, 4)),
        'null_text_input_ids': torch.randint(0, 100, (2, 4)),
    },
    {
        'vae_person': torch.randn(2, 4),
        'vae_clothes': torch.randn(2, 4),
        'clip_image': torch.randn(3, 4),
        'drop_image_embed': torch.randn(2, 4),
        'text': "another person with different clothes",
        'text_input_ids': torch.randint(0, 100, (2, 4)),
        'null_text_input_ids': torch.randint(0, 100, (2, 4)),
    }
]

ARGS = {
    'data': data
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
image_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
muzishen/imagdressing/inference_IMAGdressing_controlnetinpainting.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thomas-wyh/fuseanypart, is pointer only (licence: NONE) · get_code("d2b9faa80b2570e4")
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 thomas-wyh/fuseanypart, 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.

make_inpaint_condition Ran
ran; our contract draft was wrong, not the code
muzishen/imagdressing/inference_IMAGdressing_controlnetinpainting.py
code served (permissive licence) · get_code("326af4dadade1455")
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 (1, 3, 4, 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 torch
import numpy as np
from PIL import Image

torch.manual_seed(0)

# Create a small RGB image (4x3 pixels)
image_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
image = Image.fromarray(image_array, mode='RGB')

# Create a corresponding mask (4x3 pixels, grayscale)
mask_array = np.random.randint(0, 256, (4, 3), dtype=np.uint8)
image_mask = Image.fromarray(mask_array, mode='L')

ARGS = {
    'image': image,
    'image_mask': image_mask,
}
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 (1, 3, 4, 3) — shape (1, 3, 4, 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
resize_img Ran
ran; our contract draft was wrong, not the code
muzishen/imagdressing/inference_IMAGdressing_controlnetinpainting.py
code served (permissive licence) · get_code("be4aa063a0baeddc")
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 Image. The image it ran in was not recorded. If your copy returns the same type 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.

from PIL import Image
import numpy as np

# Create a small test image
np.random.seed(0)
img_array = np.random.randint(0, 256, (512, 640, 3), dtype=np.uint8)
input_image = Image.fromarray(img_array)

ARGS = {
    "input_image": input_image,
    "max_side": 640,
    "min_side": 512,
    "size": None,
    "pad_to_max_side": False,
    "mode": Image.BILINEAR,
    "base_pixel_number": 64,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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, 1 later) and 3 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
image_grid 10 other papers
7 dated earlier, 3 later
2303.17870 (2023-03)
GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation
2310.04816 (2023-10)
Hacking Generative Models with Differentiable Network Bending
2310.06313 (2023-10)
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
and 7 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

Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting using latent diffusion models, significantly enhancing consumers' online shopping experience. However, existing VTON technologies neglect the need for merchants to showcase garments comprehensively, including flexible control over garments, optional faces, poses, and scenes. To address this issue, we define a virtual dressing (VD) task focused on generating freely editable human images with fixed garments and optional conditions. Meanwhile, we design a comprehensive affinity metric index (CAMI) to evaluate the consistency between generated images and reference garments. Then, we propose IMAGDressing-v1, which incorporates a garment UNet that captures semantic features from CLIP and texture features from VAE. We present a hybrid attention module, including a frozen self-attention and a trainable cross-attention, to integrate garment features from the garment UNet into a frozen denoising UNet, ensuring users can control different scenes through text. IMAGDressing-v1 can be combined with other extension plugins, such as ControlNet and IP-Adapter, to enhance the diversity and controllability of generated images. Furthermore, to address the lack of data, we release the interactive garment pairing (IGPair) dataset, containing over 300,000 pairs of clothing and dressed images, and establish a standard pipeline for data assembly. Extensive experiments demonstrate that our IMAGDressing-v1 achieves state-of-the-art human image synthesis performance under various controlled conditions. The code and model will be available at https://github.com/muzishen/IMAGDressing.

For agents

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

get_harvested_code_for_paper("2407.12705")
get_code_for_paper("2407.12705")
have("2407.12705")

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

curl https://syntology.ai/api/ran/2407.12705.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.12705.svg)](https://syntology.ai/paper/2407.12705)

Connect an agent — have() is free.