SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.03027 · 2023

Zero-shot Image-to-Image Translation

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have no contract verdict; 0 failures of our instrument; 1 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/2302.03027.json · badge: /api/ran/2302.03027.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
pix2pixzero/pix2pix-zero canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
clean_l_sentences Ran
ran on a synthesized input
pix2pixzero/pix2pix-zero/src/utils/gradio_utils.py
code served (permissive licence) · get_code("b5b7f96baa2b94a9")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import re

def clean_l_sentences(ls):
    s = [re.sub('\\d', '', x) for x in ls]
    s = [x.replace('.', '').replace('-', '').replace(')', '').strip() for x in s]
    return s

ARGS = {
    'ls': [
        'hello123world',
        'test456.sentence-here)',
        '789another(test)',
        'plain text'
    ]
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
load_sentence_embeddings Ran
ran on a synthesized input
pix2pixzero/pix2pix-zero/src/utils/gradio_utils.py
code served (permissive licence) · get_code("2578faa2a5d91c0e")
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 3, dtype family float, shape (1, 77, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Create a minimal tokenizer stand-in
class MinimalTokenizer:
    def __init__(self):
        self.model_max_length = 77
    
    def __call__(self, text, padding=None, max_length=None, truncation=None, return_tensors=None):
        # Return a simple namespace with input_ids tensor
        class TokenizerOutput:
            def __init__(self):
                self.input_ids = torch.randint(0, 100, (1, 77))
        return TokenizerOutput()

# Create a minimal text encoder (nn.Module)
class MinimalTextEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.embed = nn.Embedding(100, 4)
    
    def forward(self, input_ids, attention_mask=None):
        # Return tuple where first element is embeddings of shape (batch, seq_len, hidden_dim)
        embedded = self.embed(input_ids)  # (1, 77, 4)
        return (embedded,)

# Create sample data
l_sentences = [
    "This is the first sentence.",
    "This is the second sentence."
]

tokenizer = MinimalTokenizer()
text_encoder = MinimalTextEncoder()
device = 'cpu'

ARGS = {
    'l_sentences': l_sentences,
    'tokenizer': tokenizer,
    'text_encoder': text_encoder,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (1, 77, 4) — shape (1, 77, 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
construct_direction Not yet run
unverified (harvested, no recorded run)
pix2pixzero/pix2pix-zero/src/utils/edit_directions.py
code served (permissive licence) · get_code("5f1dc9ccbe79d31b")
How it ran

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is hard for users to come up with a perfect text prompt that accurately describes every visual detail in the input image. Second, while existing models can introduce desirable changes in certain regions, they often dramatically alter the input content and introduce unexpected changes in unwanted regions. In this work, we propose pix2pix-zero, an image-to-image translation method that can preserve the content of the original image without manual prompting. We first automatically discover editing directions that reflect desired edits in the text embedding space. To preserve the general content structure after editing, we further propose cross-attention guidance, which aims to retain the cross-attention maps of the input image throughout the diffusion process. In addition, our method does not need additional training for these edits and can directly use the existing pre-trained text-to-image diffusion model. We conduct extensive experiments and show that our method outperforms existing and concurrent works for both real and synthetic image editing.

For agents

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

get_harvested_code_for_paper("2302.03027")
get_code_for_paper("2302.03027")
have("2302.03027")

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

curl https://syntology.ai/api/ran/2302.03027.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.03027.svg)](https://syntology.ai/paper/2302.03027)

Connect an agent — have() is free.