SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.06573 · 2023

ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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, 6 violated it and 0 have no contract verdict; 5 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/2312.06573.json · badge: /api/ran/2312.06573.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
vislearn/ControlNet-XS canonical (classifier label)
classifier basis not recorded on the link
11 ran · 1 no recorded run
FunctionStatusWhere it lives
HWC3 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vislearn/ControlNet-XS/annotator/util.py
code served (permissive licence) · get_code("f9ec7d70add02b6f")
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 3, dtype family int, shape (4, 5, 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 numpy as np

# Test case 1: 3-channel RGB image (most common case)
x_rgb = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)

# Test case 2: 1-channel grayscale image
x_gray = np.random.randint(0, 256, size=(4, 5, 1), dtype=np.uint8)

# Test case 3: 4-channel RGBA image
x_rgba = np.random.randint(0, 256, size=(4, 5, 4), dtype=np.uint8)

# Test case 4: 2D image (will be expanded to 3D with 1 channel)
x_2d = np.random.randint(0, 256, size=(4, 5), dtype=np.uint8)

# Use the RGB case as the primary test
ARGS = {
    "x": x_rgb
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
default Ran
ran, violated the contract we drafted
vislearn/ControlNet-XS/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
vislearn/ControlNet-XS/sgm/util.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
vislearn/ControlNet-XS/ldm/modules/attention.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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_string_from_tuple Ran
ran; our contract draft was wrong, not the code
vislearn/ControlNet-XS/sgm/util.py
code served (permissive licence) · get_code("2036522d462af205")
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 torch

def get_string_from_tuple(s):
    try:
        if s[0] == '(' and s[-1] == ')':
            t = eval(s)
            if type(t) == tuple:
                return t[0]
            else:
                pass
    except:
        pass
    return s

# The function takes a string parameter and checks if it's a string representation
# of a tuple, evaluates it, and returns the first element if it is a tuple.
# Otherwise it returns the input string unchanged.

ARGS = {
    "s": "('hello', 'world')"
}
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 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
is_power_of_two Ran
ran, violated the contract we drafted
vislearn/ControlNet-XS/sgm/util.py
code served (permissive licence) · get_code("3753e92206c00bb9")
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
import numpy as np

# The function is_power_of_two takes a single integer parameter n
# It checks if n is a power of 2 using bitwise operations
# We need to provide valid integer arguments to test the function

ARGS = {
    "n": 8  # 8 is 2^3, so this should return True
}
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 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
isimage Ran
ran, violated the contract we drafted
vislearn/ControlNet-XS/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
vislearn/ControlNet-XS/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
make_layers Ran
ran; our contract draft was wrong, not the code
vislearn/ControlNet-XS/annotator/openpose/model.py
code served (permissive licence) · get_code("0af8635db2bb32a2")
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 Sequential. 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
from collections import OrderedDict

torch.manual_seed(0)

# Construct a block dict that represents conv/pool layers
# Format for conv layers: layer_name -> (in_channels, out_channels, kernel_size, stride, padding)
# Format for pool layers: layer_name -> (kernel_size, stride, padding)
block = OrderedDict([
    ('conv1', (3, 16, 3, 1, 1)),
    ('conv2', (16, 32, 3, 1, 1)),
    ('pool1', (2, 2, 0)),
    ('conv3', (32, 64, 3, 1, 1)),
])

# List of layer names where ReLU should NOT be applied
no_relu_layers = ['pool1', 'conv3']

ARGS = {
    'block': block,
    'no_relu_layers': no_relu_layers,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
resize_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vislearn/ControlNet-XS/annotator/util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from DeepakSridhar/fgdm, is pointer only (licence: NOASSERTION) · get_code("50fd68f6989503c6")
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 DeepakSridhar/fgdm, 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.

uniq Ran
ran; our contract draft was wrong, not the code
vislearn/ControlNet-XS/ldm/modules/attention.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

log_txt_as_img Not yet run
unverified (harvested, no recorded run)
vislearn/ControlNet-XS/ldm/util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from DeepakSridhar/fgdm, is pointer only (licence: NOASSERTION) · get_code("6b4c1a8ce5fb7282")
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 DeepakSridhar/fgdm, 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 10 the same month, 12 later) and 0 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
262 dated earlier, 16 the same month, 202 later, 4 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
100 dated earlier, 14 the same month, 91 later, 2 same year, order not determinable · 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
64 dated earlier, 10 the same month, 99 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
45 dated earlier, 10 the same month, 58 later, 2 same year, order not determinable
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
30 dated earlier, 5 the same month, 32 later, 2 same year, order not determinable
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
27 dated earlier, 5 the same month, 27 later, 2 same year, order not determinable
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
HWC3 18 other papers
5 dated earlier, 2 the same month, 11 later
2305.10973 (2023-05)
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
2305.16322 (2023-05)
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
and 15 more not named here
resize_image 13 other papers
4 dated earlier, 1 the same month, 8 later
2305.16322 (2023-05)
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
2308.09592 (2023-08)
StableVideo: Text-driven Consistency-aware Diffusion Video Editing
and 10 more not named here
log_txt_as_img 8 other papers
1 dated earlier, 3 the same month, 4 later
2305.02034 (2023-05)
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
2312.04831 (2023-12)
Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency
2312.06607 (2023-12)
DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection
and 5 more not named here
make_layers 6 other papers
3 dated earlier, 2 the same month, 1 later
2305.16322 (2023-05)
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
2310.13165 (2023-10)
CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
and 3 more not named here
get_string_from_tuple 4 other papers
1 dated earlier, 3 later
2311.16813 (2023-11)
Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
04534 (2024 (year only))
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
and 1 more not named here
is_power_of_two 4 other papers
1 dated earlier, 3 later
2311.16813 (2023-11)
Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
04534 (2024 (year only))
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
and 1 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

The field of image synthesis has made tremendous strides forward in the last years. Besides defining the desired output image with text-prompts, an intuitive approach is to additionally use spatial guidance in form of an image, such as a depth map. In state-of-the-art approaches, this guidance is realized by a separate controlling model that controls a pre-trained image generation network, such as a latent diffusion model. Understanding this process from a control system perspective shows that it forms a feedback-control system, where the control module receives a feedback signal from the generation process and sends a corrective signal back. When analysing existing systems, we observe that the feedback signals are timely sparse and have a small number of bits. As a consequence, there can be long delays between newly generated features and the respective corrective signals for these features. It is known that this delay is the most unwanted aspect of any control system. In this work, we take an existing controlling network (ControlNet) and change the communication between the controlling network and the generation process to be of high-frequency and with large-bandwidth. By doing so, we are able to considerably improve the quality of the generated images, as well as the fidelity of the control. Also, the controlling network needs noticeably fewer parameters and hence is about twice as fast during inference and training time. Another benefit of small-sized models is that they help to democratise our field and are likely easier to understand. We call our proposed network ControlNet-XS. When comparing with the state-of-the-art approaches, we outperform them for pixel-level guidance, such as depth, canny-edges, and semantic segmentation, and are on a par for loose keypoint-guidance of human poses. All code and pre-trained models will be made publicly available.

For agents

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

get_harvested_code_for_paper("2312.06573")
get_code_for_paper("2312.06573")
have("2312.06573")

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

curl https://syntology.ai/api/ran/2312.06573.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.06573.svg)](https://syntology.ai/paper/2312.06573)

Connect an agent — have() is free.