SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.09800 · 2022

InstructPix2Pix: Learning to Follow Image Editing Instructions

Alexei Efros, Aleksander Holynski, Tim Brooks

arXiv · PDF · Open in the Atlas

Code that ran

17 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 5 violated it and 4 have no contract verdict; 6 failures of our instrument; 3 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/2211.09800.json · badge: /api/ran/2211.09800.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
xuduo35/InstructPix2Pix community (classifier label)
classifier basis not recorded on the link
14 ran · 0 no recorded run
mv-lab/InstructIR community
Papers with Code archive
2 ran · 1 no recorded run
mahdip72/InstructPix2Pix community
Papers with Code archive
1 ran · 0 no recorded run
lsl001006/zone community
Papers with Code archive
0 ran · 2 no recorded run
FunctionStatusWhere it lives
InstructIR Ran
ran on a synthesized input · constructed an object; no result was computed
mv-lab/InstructIR/models/instructir.py
code served (permissive licence) · get_code("da8184593ecc419a")
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 an instance of its own class, InstructIR: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "img_channel": 3,
    "width": 16,
    "middle_blk_num": 1,
    "enc_blk_nums": [1, 1],
    "dec_blk_nums": [1, 1],
    "txtdim": 768,
}
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 InstructIR — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a InstructIR 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
NAFBlock Ran
ran on a synthesized input · constructed an object; no result was computed
mv-lab/InstructIR/models/instructir.py
code served (permissive licence) · get_code("359c5485e870e3e6")
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 an instance of its own class, NAFBlock: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'c': 4,
    'DW_Expand': 2,
    'FFN_Expand': 2,
    'drop_out_rate': 0.0
}
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 NAFBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a NAFBlock 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
adapt_unet_for_pix2pix Ran
ran; our contract draft was wrong, not the code
mahdip72/InstructPix2Pix/instruct_pix2pix/model.py
code served (permissive licence) · get_code("569fbf037c75f18b")
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) and returned MockUNet. 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
import torch.nn as nn

torch.manual_seed(0)

class MockUNet(nn.Module):
    def __init__(self):
        super().__init__()
        # Create a conv_in layer with 4 input channels and 64 output channels
        self.conv_in = nn.Conv2d(
            in_channels=4,
            out_channels=64,
            kernel_size=3,
            stride=1,
            padding=1
        )
        self.config = {}
    
    def register_to_config(self, **kwargs):
        """Mock method to register config parameters"""
        self.config.update(kwargs)

# Create a mock UNet instance
unet = MockUNet()

ARGS = {
    "unet": unet
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockUNet — a MockUNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockUNet 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
always Ran
ran; our contract draft was wrong, not the code
xuduo35/InstructPix2Pix/ldm/modules/x_transformer.py
code served (permissive licence) · get_code("fe5dd5258046898c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned function. 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.

ARGS = {
    'val': 42
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
center_crop Ran
ran on a synthesized input
xuduo35/InstructPix2Pix/stable_txt2img.py
code served (permissive licence) · get_code("81aae1af1d3e0807")
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 2, dtype family float, shape (3, 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

torch.manual_seed(0)

# The function expects an image-like object with .shape attribute
# that supports integer indexing with slices
# Create a small image array (height=4, width=3)
img = np.random.rand(4, 3)

ARGS = {
    "img": img
}
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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
chunk Ran
ran; our contract draft was wrong, not the code
xuduo35/InstructPix2Pix/stable_txt2img.py
pointer only (licence: MIT); the stored copy get_code serves, from vicgalle/stable-diffusion-aesthetic-gradients, is pointer only (licence: NOASSERTION) · get_code("8241c0562bc710fd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vicgalle/stable-diffusion-aesthetic-gradients, and GitHub could not classify the licence of that repository (NOASSERTION). 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 Ran
ran, violated the contract we drafted
xuduo35/InstructPix2Pix/ldm/modules/attention.py
code served (permissive licence) · get_code("424012cb37b31172")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () 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.

from inspect import isfunction

def exists(val):
    return val is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

# Test case 1: val exists (not None), d is a regular value
ARGS_1 = {
    'val': 42,
    'd': 100
}

# Test case 2: val is None, d is a regular value
ARGS_2 = {
    'val': None,
    'd': 100
}

# Test case 3: val is None, d is a function
def default_func():
    return 200

ARGS_3 = {
    'val': None,
    'd': default_func
}

# Test case 4: val exists, d is a function
ARGS_4 = {
    'val': "existing_value",
    'd': lambda: "default_value"
}

# Use one of the test cases as the final ARGS
ARGS = ARGS_3
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 int, ndim 0, dtype family int, shape () — shape () 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
disabled_train Ran
ran, violated the contract we drafted
xuduo35/InstructPix2Pix/ldm/models/diffusion/classifier.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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) and returned SimpleModel. 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
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
exists Ran
ran, violated the contract we drafted
xuduo35/InstructPix2Pix/ldm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, 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_bert_token_for_string Ran
ran, honoured the contract we drafted
xuduo35/InstructPix2Pix/ldm/modules/embedding_manager.py
code served (permissive licence) · get_code("d5726f9e3a5684c3")
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) and returned Tensor, ndim 0, dtype family int, shape () 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)

class MockTokenizer:
    def __call__(self, string):
        # Return a tensor of shape (1, 3) with 3 non-zero tokens
        # This satisfies the assertion that torch.count_nonzero(token) == 3
        return torch.tensor([[101, 2054, 102]], dtype=torch.long)

tokenizer = MockTokenizer()
string = "hello world"

ARGS = {
    "tokenizer": tokenizer,
    "string": string,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 0, dtype family int, shape () — shape () 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_clip_token_for_string Ran
ran, honoured the contract we drafted
xuduo35/InstructPix2Pix/ldm/modules/embedding_manager.py
code served (permissive licence) · get_code("41c6eb3a0aa3eb46")
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) and returned Tensor, ndim 0, dtype family int, shape () 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)

class MockTokenizer:
    def __call__(self, string, truncation=True, max_length=77, return_length=True, 
                 return_overflowing_tokens=False, padding='max_length', return_tensors='pt'):
        # Create a batch encoding that returns tokens
        # The function expects tokens where all values are 49407 except for exactly 2 positions
        # Position 0 and position 1 should have different values
        tokens = torch.full((1, 77), 49407, dtype=torch.long)
        tokens[0, 0] = 49406  # Different token at position 0
        tokens[0, 1] = 50256  # Different token at position 1 (this is what gets returned)
        
        return {
            'input_ids': tokens,
            'length': torch.tensor([77])
        }

tokenizer = MockTokenizer()
string = "test"

ARGS = {
    'tokenizer': tokenizer,
    'string': string
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 0, dtype family int, shape () — shape () 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_embedding_for_clip_token Ran
ran; our contract draft was wrong, not the code
xuduo35/InstructPix2Pix/ldm/modules/embedding_manager.py
code served (permissive licence) · get_code("71c2df28a1008d03")
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) and returned Tensor, ndim 1, dtype family float, shape (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 SimpleEmbedder(nn.Module):
    def __init__(self):
        super().__init__()
        self.embedding = nn.Linear(1, 4)
    
    def forward(self, x):
        # x shape: (batch_size, 1)
        # output shape: (batch_size, 1, 4)
        out = self.embedding(x)
        return out.unsqueeze(1)

embedder = SimpleEmbedder()
token = torch.tensor([1], dtype=torch.float32)

ARGS = {
    "embedder": embedder,
    "token": token,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (4,) — shape (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
isimage Ran
ran, violated the contract we drafted
xuduo35/InstructPix2Pix/ldm/util.py
code served (permissive licence) · get_code("b1368330cf0f5642")
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 bool, ndim 0, dtype family float, shape () 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)

# The function isimage checks if x is a torch.Tensor with 4 dimensions
# and the second dimension (channel dim) is either 3 or 1
# Test case: valid image tensor with shape (batch, channels, height, width)
x = torch.randn(2, 3, 4, 5)

ARGS = {
    "x": x
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
ismap Ran
ran, violated the contract we drafted
xuduo35/InstructPix2Pix/ldm/util.py
code served (permissive licence) · get_code("d72762b700feee6f")
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 bool, ndim 0, dtype family float, shape () 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)

# The function checks if x is a torch.Tensor with 4 dimensions where the second dimension (x.shape[1]) is > 3
# We need to construct a tensor that satisfies this condition

# Create a tensor with shape (batch=2, channels=5, height=4, width=3)
# This has 4 dimensions and x.shape[1] = 5 > 3, so it should return True
x = torch.randn(2, 5, 4, 3)

ARGS = {
    'x': x
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
log_txt_as_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xuduo35/InstructPix2Pix/ldm/util.py
pointer only (licence: MIT); the stored copy get_code serves, from ai-med/stablepose, is pointer only (licence: GPL-3.0) · get_code("f41710299c49d36d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ai-med/stablepose, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

prune_checkpoint Ran
ran on a synthesized input
xuduo35/InstructPix2Pix/ldm/pruner.py
code served (permissive licence) · get_code("9aee358ca7c31dbc")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small state dict with model weights and optimizer states
old_state = {
    'state_dict': {
        'layer1.weight': torch.randn(4, 3),
        'layer1.bias': torch.randn(4),
        'layer2.weight': torch.randn(5, 4),
    },
    'optimizer_states': {
        'momentum': torch.randn(4, 3),
    },
    'global_step': 42,
    'epoch': 5,
}

ARGS = {
    'old_state': old_state,
}
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
uniq Ran
ran; our contract draft was wrong, not the code
xuduo35/InstructPix2Pix/ldm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from JingWu321/MUNBa, is pointer only (licence: NONE) · get_code("9a299fe5ae09e407")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from JingWu321/MUNBa, 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.

ICB Not yet run
unverified (harvested, no recorded run)
mv-lab/InstructIR/models/instructir.py
code served (permissive licence) · get_code("4a0143b046f97246")
How it ran

no invocation recorded.

register_attention_control Not yet run
unverified (harvested, no recorded run)
lsl001006/zone/null_text_w_ptp.py
code served (permissive licence) · get_code("48d7b99aa07d02fe")
How it ran

no invocation recorded.

text2image_instructpix2pix Not yet run
unverified (harvested, no recorded run)
lsl001006/zone/null_text_w_ptp.py
code served (permissive licence) · get_code("70183cfe0ed40ffb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 14 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 4 the same month, 14 later) and 6 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
exists 486 other papers
126 dated earlier, 3 the same month, 354 later, 1 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
26 dated earlier, 1 the same month, 180 later · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
disabled_train 173 other papers
12 dated earlier, 1 the same month, 160 later · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
uniq 115 other papers
6 dated earlier, 109 later
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2206.02779 (2022-06)
Blended Latent Diffusion
and 112 more not named here
ismap 69 other papers
4 dated earlier, 65 later
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2206.02779 (2022-06)
Blended Latent Diffusion
2208.13753 (2022-08)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
and 66 more not named here
isimage 61 other papers
3 dated earlier, 58 later
2206.02779 (2022-06)
Blended Latent Diffusion
2208.13753 (2022-08)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
2210.12965 (2022-10)
High-Resolution Image Editing via Multi-Stage Blended Diffusion
and 58 more not named here
always 56 other papers
7 dated earlier, 49 later
2102.12092 (2021-02)
Zero-Shot Text-to-Image Generation
2107.03312 (2021-07)
SoundStream: An End-to-End Neural Audio Codec
2206.00100 (2022-06)
VALHALLA: Visual Hallucination for Machine Translation
and 53 more not named here
chunk 40 other papers
7 dated earlier, 1 the same month, 32 later
2106.14490 (2021-06)
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.11824 (2022-04)
Semi-Parametric Neural Image Synthesis
and 37 more not named here
get_bert_token_for_string 11 other papers
2 dated earlier, 9 later
2208.01618 (2022-08)
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
2210.09477 (2022-10)
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
2212.04489 (2022-12)
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
and 8 more not named here
get_clip_token_for_string 9 other papers
2 dated earlier, 7 later
2208.01618 (2022-08)
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
2210.09477 (2022-10)
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
2212.04489 (2022-12)
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
and 6 more not named here
get_embedding_for_clip_token 9 other papers
2 dated earlier, 7 later
2208.01618 (2022-08)
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
2210.09477 (2022-10)
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
2212.04489 (2022-12)
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
and 6 more not named here
NAFBlock
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 4 only as an assembly brick
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.16425 (2023-03)
Real-time Controllable Denoising for Image and Video
2308.13783 (2023-08)
Generalized Lightness Adaptation with Channel Selective Normalization
and 1 more not named here
log_txt_as_img 4 other papers
4 later
2303.18181 (2023-03)
A Closer Look at Parameter-Efficient Tuning in Diffusion Models
2305.16225 (2023-05)
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
2306.00971 (2023-06)
ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation
and 1 more not named here
center_crop 1 other paper
1 later
aaai_28565 (2024 (year only))
Compositional Inversion for Stable Diffusion Models

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

Replace the fruits with cake" "Make his jacket out of leather" "Add fireworks to the sky" "Turn it into a still from a western" "Swap sunflowers with roses" "What would it look like if it were snowing?" Figure 1. Given an image and an instruction for how to edit that image, our model performs the appropriate edit. Our model does not require full descriptions for the input or output image, and edits images in the forward pass without per-example inversion or fine-tuning.

For agents

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

get_harvested_code_for_paper("2211.09800")
get_code_for_paper("2211.09800")
have("2211.09800")

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

curl https://syntology.ai/api/ran/2211.09800.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.09800.svg)](https://syntology.ai/paper/2211.09800)

Connect an agent — have() is free.