SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.10752 · CVPR · 2021

High-Resolution Image Synthesis with Latent Diffusion Models

Björn Ommer, Robin Rombach, Patrick Esser, Andreas Blattmann, Dominik Lorenz

arXiv · PDF · Open in the Atlas

Code that ran

22 of 28 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, 4 violated it and 2 have no contract verdict; 15 failures of our instrument; 6 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2112.10752.json · badge: /api/ran/2112.10752.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
lorenzo-stacchio/Stable-Diffusion-Inpaint community (classifier label)
classifier basis: plan_row
10 ran · 2 no recorded run
yangling0818/contextdiff extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
explainingai-code/StableDiffusion-PyTorch community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
spengliang/smoothvideo community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
labmlai/annotated_deep_learning_paper_implementations reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
zgctroy/layoutdiffusion reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
interpolate_fn Ran
ran; our contract draft was wrong, not the code
lorenzo-stacchio/Stable-Diffusion-Inpaint/ldm/models/diffusion/dpm_solver/dpm_solver.py
code served (permissive licence) · get_code("6a35b62fbc80f70a")
How it ran

Ran in Syntology's jail 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 (2, 1) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:15:28Z). 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)

# x: PyTorch tensor with shape [N, C], where N is batch size, C is number of channels
x = torch.randn(2, 1)

# xp: PyTorch tensor with shape [C, K], where K is number of keypoints
xp = torch.linspace(0, 1, 4).unsqueeze(0).repeat(1, 1)  # shape [1, 4]

# yp: PyTorch tensor with shape [C, K]
yp = torch.linspace(0, 2, 4).unsqueeze(0).repeat(1, 1)  # shape [1, 4]

ARGS = {
    "x": x,
    "xp": xp,
    "yp": yp,
}
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 (2, 1) — shape (2, 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
bits_to_decimal Ran
ran; our contract draft was wrong, not the code
yangling0818/contextdiff/ContextDiff_image/diffusers/examples/community/bit_diffusion.py
pointer only (licence: NONE) · get_code("71cce9a0eff16fa1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yangling0818/contextdiff 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.

chunk Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from vicgalle/stable-diffusion-aesthetic-gradients
pointer only; 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 copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

decimal_to_bits Ran
ran; our contract draft was wrong, not the code
yangling0818/contextdiff/ContextDiff_image/diffusers/examples/community/bit_diffusion.py
pointer only (licence: NONE) · get_code("92770f5c18857083")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yangling0818/contextdiff 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 Ran
ran, violated the contract we drafted
lorenzo-stacchio/Stable-Diffusion-Inpaint/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
lorenzo-stacchio/Stable-Diffusion-Inpaint/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
lorenzo-stacchio/Stable-Diffusion-Inpaint/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.

expand_dims Ran
ran; our contract draft was wrong, not the code
lorenzo-stacchio/Stable-Diffusion-Inpaint/ldm/models/diffusion/dpm_solver/dpm_solver.py
code served (permissive licence) · get_code("e6110366588c5c65")
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, 1, 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)

# Create a small 1D tensor with shape [N]
v = torch.randn(2)

# Create a dims parameter - total number of dimensions desired
dims = 4

ARGS = {
    "v": v,
    "dims": dims,
}
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, 1, 1, 1) — shape (2, 1, 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
get_config_value Ran
ran, honoured the contract we drafted
explainingai-code/StableDiffusion-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_noise_pred_single Ran
ran; our contract draft was wrong, not the code
spengliang/smoothvideo/tuneavideo/util.py
code served (permissive licence) · get_code("0b088617d5525751")
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)

# Build a minimal UNet that accepts latents, t, and encoder_hidden_states
class MiniUNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, latents, t, encoder_hidden_states=None):
        # latents: [batch, channels]
        # t: scalar or tensor
        # encoder_hidden_states: [batch, seq_len, hidden_dim]
        # Return dict with 'sample' key
        noise_pred = self.linear(latents)
        return {'sample': noise_pred}

# Create instances
latents = torch.randn(2, 4)  # batch=2, channels=4
t = torch.tensor(5)  # timestep
context = torch.randn(2, 3, 5)  # batch=2, seq_len=3, hidden_dim=5
unet = MiniUNet()

ARGS = {
    'latents': latents,
    't': t,
    'context': context,
    'unet': unet
}
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
get_time_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
explainingai-code/StableDiffusion-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_batch Ran
ran on a synthesized input
lorenzo-stacchio/Stable-Diffusion-Inpaint/inpaint_utils.py
code served (permissive licence) · get_code("af3d3fd0371ecf63")
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. 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 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
from PIL import Image
import tempfile
import os

torch.manual_seed(0)

# Create temporary directory for test images
temp_dir = tempfile.mkdtemp()

# Create a simple RGB test image
rgb_image = Image.new('RGB', (64, 64), color=(100, 150, 200))
image_path = os.path.join(temp_dir, 'test_image.png')
rgb_image.save(image_path)

# Create a simple grayscale mask image
mask_image = Image.new('L', (64, 64), color=200)
mask_path = os.path.join(temp_dir, 'test_mask.png')
mask_image.save(mask_path)

ARGS = {
    'image': image_path,
    'mask': mask_path,
    'device': 'cpu',
    'resize_to': 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy, 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
model_wrapper Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lorenzo-stacchio/Stable-Diffusion-Inpaint/ldm/models/diffusion/dpm_solver/dpm_solver.py
pointer only (licence: MIT); the stored copy get_code serves, from wl-zhao/dc-solver, is pointer only (licence: NONE) · get_code("c38c4cd486f7a766")
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 wl-zhao/dc-solver, 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.

next_step Ran
ran; our contract draft was wrong, not the code
spengliang/smoothvideo/tuneavideo/util.py
code served (permissive licence) · get_code("fb032d6fa7e6196d")
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)

class DDIMSchedulerConfig:
    def __init__(self):
        self.num_train_timesteps = 1000

class DDIMScheduler:
    def __init__(self):
        self.config = DDIMSchedulerConfig()
        self.num_inference_steps = 50
        # Create alphas_cumprod with 1000 timesteps
        self.alphas_cumprod = torch.linspace(0.9999, 0.0001, 1000)
        self.final_alpha_cumprod = torch.tensor(0.0)

model_output = torch.randn(2, 4)
timestep = 500
sample = torch.randn(2, 4)
ddim_scheduler = DDIMScheduler()

ARGS = {
    "model_output": model_output,
    "timestep": timestep,
    "sample": sample,
    "ddim_scheduler": ddim_scheduler
}
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
normalization Ran
ran; our contract draft was wrong, not the code
labmlai/annotated_deep_learning_paper_implementations/labml_nn/diffusion/stable_diffusion/model/autoencoder.py
code served (permissive licence) · get_code("08dcc8265812cbef")
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 GroupNorm. 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
from torch import nn

torch.manual_seed(0)

# The function expects an integer for channels
# It will create a GroupNorm with 32 groups, so channels should be divisible by 32
# Let's use 64 channels as a valid example
channels = 64

ARGS = {
    'channels': channels
}
Setup block drafted by
a language model, Claude Sonnet 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 GroupNorm — a GroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm 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
numpy_to_pil Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from vicgalle/stable-diffusion-aesthetic-gradients
pointer only; the stored copy get_code serves, from vicgalle/stable-diffusion-aesthetic-gradients, is pointer only (licence: NOASSERTION) · get_code("1e63d588563eb90a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

plot_row_original_mask_output Ran
ran on a synthesized input
lorenzo-stacchio/Stable-Diffusion-Inpaint/inpaint_utils.py
code served (permissive licence) · get_code("e4de1fdad679dd5c")
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 (1024, 1536, 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
import cv2
from typing import List, Dict

torch.manual_seed(0)

# Create sample images for the list_tuple
# The function expects a List[Dict] where each dict has string keys (like 'original', 'mask', 'output')
# and the values are numpy arrays representing images

# Create small sample images (grayscale and RGB)
sample_gray = np.random.randint(0, 256, (256, 256), dtype=np.uint8)
sample_rgb = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)

# Construct the list_tuple as List[Dict]
list_tuple = [
    {
        'original': sample_rgb.copy(),
        'mask': sample_gray.copy(),
        'output': sample_rgb.copy()
    },
    {
        'original': sample_rgb.copy(),
        'mask': sample_gray.copy(),
        'output': sample_rgb.copy()
    }
]

ARGS = {
    'list_tuple': list_tuple,
    'image_size': 512
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 3, dtype family int, shape (1024, 1536, 3) — shape (1024, 1536, 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
spatial_average Ran
ran; our contract draft was wrong, not the code
explainingai-code/StableDiffusion-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
spherical_dist_loss Ran
ran; our contract draft was wrong, not the code
yangling0818/contextdiff/ContextDiff_image/diffusers/examples/community/clip_guided_stable_diffusion.py
pointer only (licence: NONE) · get_code("36a34f4a30080b93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yangling0818/contextdiff 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.

swish Ran
ran; our contract draft was wrong, not the code
labmlai/annotated_deep_learning_paper_implementations/labml_nn/diffusion/stable_diffusion/model/autoencoder.py
code served (permissive licence) · get_code("8efb92cd06aefbfb")
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 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

torch.manual_seed(0)

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Sonnet 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 (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
uniform_on_device Ran
ran; our contract draft was wrong, not the code
lorenzo-stacchio/Stable-Diffusion-Inpaint/ldm/models/diffusion/ddpm.py
code served (permissive licence) · get_code("d48d8354986e3b0e")
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 (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

torch.manual_seed(0)

# Analyze the function:
# - r1: used in arithmetic (r1 - r2), should be a scalar or tensor
# - r2: used in arithmetic (r1 - r2), should be a scalar or tensor
# - shape: unpacked with *shape in torch.rand(*shape, device=device), should be a tuple/list of ints
# - device: passed to torch.rand, should be a valid torch device

ARGS = {
    "r1": 2.0,
    "r2": 1.0,
    "shape": (2, 4),
    "device": torch.device("cpu")
}
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 (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
uniq Ran
ran; our contract draft was wrong, not the code
lorenzo-stacchio/Stable-Diffusion-Inpaint/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.

build_model Not yet run
unverified (harvested, no recorded run)
zgctroy/layoutdiffusion/layout_diffusion/layout_diffusion_unet.py
code served (permissive licence) · get_code("f07113626bc2a9ae")
How it ran

no invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
spengliang/smoothvideo/tuneavideo/models/unet_blocks.py
code served (permissive licence) · get_code("a362e5b7a1be4609")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
spengliang/smoothvideo/tuneavideo/models/unet_blocks.py
code served (permissive licence) · get_code("01feceecb56a7ffb")
How it ran

no invocation recorded.

init_prompt Not yet run
unverified (harvested, no recorded run)
spengliang/smoothvideo/tuneavideo/util.py
code served (permissive licence) · get_code("a0a4d94af120c56f")
How it ran

no invocation recorded.

nondefault_trainer_args Not yet run
unverified (harvested, no recorded run)
lorenzo-stacchio/Stable-Diffusion-Inpaint/main_inpainting.py
pointer only (licence: MIT); the stored copy get_code serves, from yangling0818/sgdiff, is pointer only (licence: NONE) · get_code("87fbedd0c27cf378")
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 yangling0818/sgdiff, 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.

resize_if Not yet run
unverified (harvested, no recorded run)
lorenzo-stacchio/Stable-Diffusion-Inpaint/inpaint_utils.py
code served (permissive licence) · get_code("682145f66bb2762b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 28 samples lifted from this paper's linked repositories, 28 carry a function identity and 0 do not. Of the 28 distinct functions with an identity, 22 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 22 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
72 dated earlier, 2 the same month, 410 later, 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
10 dated earlier, 1 the same month, 196 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
3 dated earlier, 1 the same month, 169 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
115 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 112 more not named here
uniform_on_device 44 other papers
44 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 41 more not named here
chunk 40 other papers
1 dated earlier, 39 later
2106.14490 (2021-06)
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
2204.11824 (2022-04)
Semi-Parametric Neural Image Synthesis
2208.12242 (2022-08)
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
and 37 more not named here
expand_dims 39 other papers
39 later · 4 only as an assembly brick
2202.09778 (2022-02)
Pseudo Numerical Methods for Diffusion Models on Manifolds
2206.00927 (2022-06)
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
2211.01095 (2022-11)
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
and 36 more not named here
interpolate_fn 34 other papers
34 later
2211.01095 (2022-11)
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
2212.09478 (2022-12)
MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation
2301.11798 (2023-01)
MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer
and 31 more not named here
numpy_to_pil 23 other papers
1 dated earlier, 22 later
2106.14490 (2021-06)
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
2209.12330 (2022-09)
Personalizing Text-to-Image Generation via Aesthetic Gradients
2210.06886 (2022-10)
ImaginaryNet: Learning Object Detectors without Real Images and Annotations
and 20 more not named here
spatial_average 19 other papers
7 dated earlier, 12 later
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
init_prompt 14 other papers
14 later
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
2305.13077 (2023-05)
ControlVideo: Training-free Controllable Text-to-Video Generation
and 11 more not named here
next_step 11 other papers
11 later
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
2307.04725 (2023-07)
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
and 8 more not named here
get_down_block 10 other papers
10 later
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
2305.13077 (2023-05)
ControlVideo: Training-free Controllable Text-to-Video Generation
and 7 more not named here
get_up_block 10 other papers
10 later
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
2305.13077 (2023-05)
ControlVideo: Training-free Controllable Text-to-Video Generation
and 7 more not named here
get_noise_pred_single 8 other papers
8 later
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
2307.04725 (2023-07)
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
and 5 more not named here
nondefault_trainer_args 8 other papers
1 dated earlier, 7 later
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2211.13319 (2022-11)
Make-A-Story: Visual Memory Conditioned Consistent Story Generation
2303.18181 (2023-03)
A Closer Look at Parameter-Efficient Tuning in Diffusion Models
and 5 more not named here
model_wrapper 6 other papers
6 later
aaai_28147 (2024 (year only))
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
2401.11708 (2024-01)
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
2406.18361 (2024-06)
Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Process
and 3 more not named here
get_time_embedding 4 other papers
1 dated earlier, 3 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2302.05543 (2023-02)
Adding Conditional Control to Text-to-Image 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
2 later
2302.05543 (2023-02)
Adding Conditional Control to Text-to-Image Diffusion Models
2603.04340 (2026-03)
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
build_model 1 other paper
1 later
2303.17189 (2023-03)
LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation

Shown: the 20 functions present in the most other papers. 2 more shared functions are not listed 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

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state-of-the-art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including text-to-image synthesis, unconditional image generation and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

For agents

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

get_harvested_code_for_paper("2112.10752")
get_code_for_paper("2112.10752")
have("2112.10752")

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

curl https://syntology.ai/api/ran/2112.10752.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.10752.svg)](https://syntology.ai/paper/2112.10752)

Connect an agent — have() is free.