SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.05543 · ICCV · 2023

Adding Conditional Control to Text-to-Image Diffusion Models

Anyi Rao, Lvmin Zhang, Maneesh Agrawala

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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 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/2302.05543.json · badge: /api/ran/2302.05543.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
explainingai-code/ControlNet-PyTorch community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
get_config_value Ran
ran, honoured the contract we drafted
explainingai-code/ControlNet-PyTorch/utils/config_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vlbthambawita/SynCMRI, is pointer only (licence: NONE) · get_code("97f9c554227c4d08")
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 vlbthambawita/SynCMRI, 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_time_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
explainingai-code/ControlNet-PyTorch/models/blocks.py
code served (permissive licence) · get_code("d3705ec829eb39f1")
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 2, dtype family float, shape (4, 8) 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)

# time_steps: 1D tensor of length batch size
time_steps = torch.tensor([0, 5, 10, 15], dtype=torch.float32)

# temb_dim: Dimension of the embedding (must be divisible by 2)
temb_dim = 8

ARGS = {
    "time_steps": time_steps,
    "temb_dim": temb_dim,
}
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 2, dtype family float, shape (4, 8) — shape (4, 8) 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
make_zero_module Ran
ran on a synthesized input
explainingai-code/ControlNet-PyTorch/models/controlnet.py
code served (permissive licence) · get_code("cc09ac4f5193b11a")
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 SimpleModule. 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 simple nn.Module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Instantiate the module
module = SimpleModule()

# Verify it has parameters with non-zero values
for p in module.parameters():
    p.data.fill_(1.0)

ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
spatial_average Ran
ran; our contract draft was wrong, not the code
explainingai-code/ControlNet-PyTorch/models/lpips.py
code served (permissive licence) · get_code("29e5e72bcd006dcd")
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 4, dtype family float, shape (2, 4, 1, 1) 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 performs spatial averaging on a 4D tensor (batch, channels, height, width)
# by taking the mean over dimensions 2 and 3 (height and width)
in_tens = torch.randn(2, 4, 3, 5)  # batch=2, channels=4, height=3, width=5

ARGS = {
    "in_tens": in_tens,
    "keepdim": 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 Tensor, ndim 4, dtype family float, shape (2, 4, 1, 1) — shape (2, 4, 1, 1) 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
spatial_average 19 other papers
9 dated earlier, 9 later, 1 same year, order not determinable
1801.03924 (2018-01)
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2002.09219 (2020-02)
Stochastic Latent Residual Video Prediction
and 16 more not named here
get_time_embedding 4 other papers
2 dated earlier, 2 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2603.04340 (2026-03)
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
and 1 more not named here
get_config_value 2 other papers
1 dated earlier, 1 later
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2603.04340 (2026-03)
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study

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

"masterpiece of fairy tale, giant deer, golden antlers" Input human pose Default "chef in kitchen" "…, quaint city Galic" "Lincoln statue" Figure 1: Controlling Stable Diffusion with learned conditions. ControlNet allows users to add conditions like Canny edges (top), human pose (bottom), etc., to control the image generation of large pretrained diffusion models. The default results use the prompt "a high-quality, detailed, and professional image". Users can optionally give prompts like the "chef in kitchen".

For agents

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

get_harvested_code_for_paper("2302.05543")
get_code_for_paper("2302.05543")
have("2302.05543")

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

curl https://syntology.ai/api/ran/2302.05543.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.05543.svg)](https://syntology.ai/paper/2302.05543)

Connect an agent — have() is free.