SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.14352 · ICCV · 2023

General Image-to-Image Translation with One-Shot Image Guidance

Yue Lin, Bin Cheng, Zuhao Liu, Yunbo Peng

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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; 6 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2307.14352.json · badge: /api/ran/2307.14352.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
crystalneuro/visual-concept-translator canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
backward_ddim Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/ddim_inversion.py
code served (permissive licence) · get_code("a3379285d38d5ba2")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Construct valid arguments for backward_ddim
x_t = torch.randn(2, 4)  # batch_size=2, dim=4
alpha_t = torch.tensor(0.9)  # scalar tensor for alpha_t
alpha_tm1 = torch.tensor(0.8)  # scalar tensor for alpha_{t-1}
eps_xt = torch.randn(2, 4)  # batch_size=2, dim=4, same shape as x_t

ARGS = {
    "x_t": x_t,
    "alpha_t": alpha_t,
    "alpha_tm1": alpha_tm1,
    "eps_xt": eps_xt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/new_scheduling_ddpm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gulucaptain/videoassembler, is pointer only (licence: NONE) · get_code("c3d321eafd7ea5fc")
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 gulucaptain/videoassembler, 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.

default_score_estimation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
crystalneuro/visual-concept-translator/ptp_inversion.py
code served (permissive licence) · get_code("653217e1d54a411b")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

class MockUNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, latent_model_input, t, encoder_hidden_states):
        # Process input and return dict with 'sample' key
        batch_size = latent_model_input.shape[0]
        output = self.linear(latent_model_input)
        return {'sample': output}

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.unet = MockUNet()

# Create instances
model = MockModel()
latents = torch.randn(2, 4)
context = torch.randn(3, 5)
t = torch.tensor([10, 20])
guidance_scale = 7.5
do_classifier_free_guidance = True

ARGS = {
    'model': model,
    'latents': latents,
    'context': context,
    't': t,
    'guidance_scale': guidance_scale,
    'do_classifier_free_guidance': do_classifier_free_guidance
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
forward_ddim Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/ddim_inversion.py
code served (permissive licence) · get_code("85fd2e71002a15f4")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Construct arguments for forward_ddim
# The function takes: x_t, alpha_t, alpha_tp1, eps_xt
# All appear to be tensors used in mathematical operations

x_t = torch.randn(2, 4)  # batch size 2, dimension 4
alpha_t = torch.tensor(0.9)  # scalar tensor for alpha_t
alpha_tp1 = torch.tensor(0.85)  # scalar tensor for alpha_{t+1}
eps_xt = torch.randn(2, 4)  # batch size 2, dimension 4, same shape as x_t

ARGS = {
    "x_t": x_t,
    "alpha_t": alpha_t,
    "alpha_tp1": alpha_tp1,
    "eps_xt": eps_xt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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_matrix Ran
ran; our contract draft was wrong, not the code
crystalneuro/visual-concept-translator/seq_aligner.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Supercomputing-System-AI-Lab/InstantEdit, is pointer only (licence: NONE) · get_code("d167441d997c52ce")
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 Supercomputing-System-AI-Lab/InstantEdit, 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.

get_matrix Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/seq_aligner.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Supercomputing-System-AI-Lab/InstantEdit, is pointer only (licence: NONE) · get_code("81db21bf982ca0fe")
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 Supercomputing-System-AI-Lab/InstantEdit, 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.

get_out_img_path Ran
ran; our contract draft was wrong, not the code
crystalneuro/visual-concept-translator/pivot_turning_inversion.py
code served (permissive licence) · get_code("56b072a98a341ab0")
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 str. 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 os
import tempfile
import shutil

# Create temporary directories for testing
temp_out_dir = tempfile.mkdtemp()
temp_input_dir = tempfile.mkdtemp()

# Create some dummy files in the output directory so len(os.listdir(out_path)) > 0
for i in range(3):
    open(os.path.join(temp_out_dir, f"dummy_{i}.jpg"), 'w').close()

# Create a dummy input image path
input_img_path = os.path.join(temp_input_dir, "test_image.jpg")
open(input_img_path, 'w').close()

ARGS = {
    'out_path': temp_out_dir,
    'input_img_path': input_img_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_traceback_matrix Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/seq_aligner.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Supercomputing-System-AI-Lab/InstantEdit, is pointer only (licence: NONE) · get_code("beb8f6a30678a4d9")
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 Supercomputing-System-AI-Lab/InstantEdit, 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.

image_grid_three_groups Ran
ran; our contract draft was wrong, not the code
crystalneuro/visual-concept-translator/pivot_turning_inversion.py
code served (permissive licence) · get_code("36a016cfede1b253")
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

# Create small RGB images with distinct dimensions
# The function accesses .size on the first image and pastes images onto a grid
# We need 3 groups of images, each group having the same number of images

img_width = 64
img_height = 48

# Create sample images for group 1
imgs_group1 = [
    Image.new('RGB', size=(img_width, img_height), color=(255, 0, 0)),
    Image.new('RGB', size=(img_width, img_height), color=(255, 50, 0)),
]

# Create sample images for group 2
imgs_group2 = [
    Image.new('RGB', size=(img_width, img_height), color=(0, 255, 0)),
    Image.new('RGB', size=(img_width, img_height), color=(50, 255, 0)),
]

# Create sample images for group 3
imgs_group3 = [
    Image.new('RGB', size=(img_width, img_height), color=(0, 0, 255)),
    Image.new('RGB', size=(img_width, img_height), color=(50, 0, 255)),
]

ARGS = {
    'imgs_group1': imgs_group1,
    'imgs_group2': imgs_group2,
    'imgs_group3': imgs_group3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — 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
image_grid_two_groups Ran
ran; our contract draft was wrong, not the code
crystalneuro/visual-concept-translator/pivot_turning_inversion.py
code served (permissive licence) · get_code("4a169ba2b27d7e15")
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

# Create small test images
def create_test_image(width, height, color):
    """Create a simple RGB image with a solid color."""
    return Image.new('RGB', (width, height), color)

# Create two groups of images with the same count
# Using distinct sizes: 8 width, 6 height for each image
img_width = 8
img_height = 6
num_images = 3

# Group 1: Red-tinted images
imgs_group1 = [
    create_test_image(img_width, img_height, (255, 0, 0)),
    create_test_image(img_width, img_height, (200, 50, 50)),
    create_test_image(img_width, img_height, (150, 100, 100)),
]

# Group 2: Blue-tinted images
imgs_group2 = [
    create_test_image(img_width, img_height, (0, 0, 255)),
    create_test_image(img_width, img_height, (50, 50, 200)),
    create_test_image(img_width, img_height, (100, 100, 150)),
]

ARGS = {
    'imgs_group1': imgs_group1,
    'imgs_group2': imgs_group2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — 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
load_img Ran
ran, honoured the contract we drafted
crystalneuro/visual-concept-translator/ddim_inversion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from tuananhbui89/Erasing-Adversarial-Preservation, is pointer only (licence: NONE) · get_code("33b9cc6eebe44312")
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 tuananhbui89/Erasing-Adversarial-Preservation, 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.

text_under_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
crystalneuro/visual-concept-translator/ptp_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from TFNTF/PostEdit, is pointer only (licence: NONE) · get_code("85d5eb123674597d")
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 TFNTF/PostEdit, 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.

aggregate_attention Not yet run
unverified (harvested, no recorded run)
crystalneuro/visual-concept-translator/ptp_inversion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from YtongXie/PairAug, is pointer only (licence: NONE) · get_code("23ca7e055397296f")
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 YtongXie/PairAug, 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.

diffusion_step Not yet run
unverified (harvested, no recorded run)
crystalneuro/visual-concept-translator/ptp_utils.py
code served (permissive licence) · get_code("72814e44d259c855")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 7 later) and 5 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
text_under_image 14 other papers
1 the same month, 13 later
2307.12493 (2023-07)
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
2309.14494 (2023-09)
Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
2311.16491 (2023-11)
$Z^*$: Zero-shot Style Transfer via Attention Rearrangement
and 11 more not named here
get_matrix 11 other papers
2 dated earlier, 9 later
2208.01626 (2022-08)
Prompt-to-Prompt Image Editing with Cross Attention Control
2305.19164 (2023-05)
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
2308.06160 (2023-08)
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
and 8 more not named here
get_traceback_matrix 10 other papers
1 dated earlier, 9 later
2305.19164 (2023-05)
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
2308.06160 (2023-08)
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
2309.14494 (2023-09)
Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
and 7 more not named here
get_matrix 9 other papers
1 dated earlier, 8 later
2305.19164 (2023-05)
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
2308.06160 (2023-08)
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
2309.14494 (2023-09)
Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
and 6 more not named here
aggregate_attention 3 other papers
1 dated earlier, 2 later
2211.09794 (2022-11)
Null-text Inversion for Editing Real Images using Guided Diffusion Models
aaai_28210 (2024 (year only))
AdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing
2404.04960 (2024-04)
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?
betas_for_alpha_bar 3 other papers
1 dated earlier, 2 later
2204.13902 (2022-04)
Fast Sampling of Diffusion Models with Exponential Integrator
2311.16711 (2023-11)
LEDITS++: Limitless Image Editing using Text-to-Image Models
2311.17338 (2023-11)
MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
backward_ddim 1 other paper
1 dated earlier
2306.14435 (2023-06)
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
forward_ddim 1 other paper
1 dated earlier
2306.14435 (2023-06)
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
load_img 1 other paper
1 later
2410.15618 (2024-10)
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

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: The image-to-image translation exhibition of the proposed visual concept translator (VCT). For each image group, the upper-left part is the source image, the lower-left part is the reference image, and the right part is the model output (target image).

For agents

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

get_harvested_code_for_paper("2307.14352")
get_code_for_paper("2307.14352")
have("2307.14352")

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

curl https://syntology.ai/api/ran/2307.14352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.14352.svg)](https://syntology.ai/paper/2307.14352)

Connect an agent — have() is free.