SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.05225 · CVPR · 2023

Domain Expansion of Image Generators

Richard Zhang, Taesung Park, Jun-Yan Zhu, Eli Shechtman, Yotam Nitzan, Daniel Cohen-Or, Michaël Gharbi

arXiv · PDF · Open in the Atlas

Code that ran

16 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (10 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 6 failures of our instrument; 10 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/2301.05225.json · badge: /api/ran/2301.05225.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
lllyasviel/controlnet community
Papers with Code archive
13 ran · 9 no recorded run
adobe-research/domain-expansion community
Papers with Code archive
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
CheckpointFunction Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("70ec8e3dd3981b5e")
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, CheckpointFunction: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Define a simple run_function that takes tensors and produces output
def simple_run_function(input_tensor):
    """A simple function that processes input tensors"""
    return input_tensor * 2 + 1

# Create small test tensors
input_tensor = torch.randn(2, 4, requires_grad=True)

# The CheckpointFunction.forward expects:
# - run_function: callable that takes input tensors
# - length: int specifying how many of the remaining args are input_tensors
# - *args: variable args split into input_tensors (first `length` items) and input_params (rest)

# For this setup:
# - run_function will be simple_run_function
# - length will be 1 (we have 1 input tensor)
# - args will be (input_tensor,) - just the one tensor, no additional params

ARGS = {
    'run_function': simple_run_function,
    'length': 1,
    'args': (input_tensor,)
}
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 CheckpointFunction — 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 CheckpointFunction 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
CrossAttention Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("87dcf207c5c9187c")
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, CrossAttention: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
from einops import rearrange, repeat

torch.manual_seed(0)

# Helper functions from the module
def exists(val):
    return val is not None

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

# Set attention precision to fp32
import os
os.environ['ATTN_PRECISION'] = 'fp32'

# Define the CrossAttention class (copying from the function definition)
class CrossAttention(nn.Module):
    def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.0):
        super().__init__()
        inner_dim = dim_head * heads
        context_dim = default(context_dim, query_dim)
        self.scale = dim_head ** (-0.5)
        self.heads = heads
        self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
        self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
        self.to_v = nn.Linear(context_dim, inner_dim, bias=False)
        self.to_out = nn.Sequential(nn.Linear(inner_dim, query_dim), nn.Dropout(dropout))

    def forward(self, x, context=None, mask=None):
        from torch import einsum
        h = self.heads
        q = self.to_q(x)
        context = default(context, x)
        k = self.to_k(context)
        v = self.to_v(context)
        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
        
        _ATTN_PRECISION = os.environ.get('ATTN_PRECISION', 'fp32')
        if _ATTN_PRECISION == 'fp32':
            with torch.autocast(enabled=False, device_type='cpu'):
                q, k = (q.float(), k.float())
                sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
        else:
            sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
        del q, k
        if exists(mask):
            mask = rearrange(mask, 'b ... -> b (...)')
            max_neg_value = -torch.finfo(sim.dtype).max
            mask = repeat(mask, 'b j -> (b h) () j', h=h)
            sim.masked_fill_(~mask, max_neg_value)
        sim = sim.softmax(dim=-1)
        out = einsum('b i j, b j d -> b i d', sim, v)
        out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
        return self.to_out(out)

# Create test inputs
batch_size = 2
seq_len_x = 3
seq_len_context = 5
query_dim = 16
context_dim = 16
heads = 4
dim_head = 4
dropout = 0.0

# x tensor: (batch, seq_len, query_dim)
x = torch.randn(batch_size, seq_len_x, query_dim)

# context tensor: (batch, seq_len_context, context_dim)
context = torch.randn(batch_size, seq_len_context, context_dim)

# mask tensor: (batch, seq_len_context) - boolean mask
mask = torch.ones(batch_size, seq_len_context, dtype=torch.bool)

ARGS = {
    'query_dim': query_dim,
    'context_dim': context_dim,
    'heads': heads,
    'dim_head': dim_head,
    'dropout': dropout
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CrossAttention — 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 CrossAttention 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
Downsample Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("0feab49c606075bb")
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, Downsample: 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 = {
    "channels": 3,
    "use_conv": True,
    "dims": 2,
    "out_channels": 5,
    "padding": 1,
}
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 Downsample — 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 Downsample 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
FeedForward Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("1ce39bf592ba310f")
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, FeedForward: 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 = {
    'dim': 8,
    'dim_out': 10,
    'mult': 4,
    'glu': False,
    'dropout': 0.1
}
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 FeedForward — 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 FeedForward 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
GEGLU Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("387673fa5780bf50")
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, GEGLU: 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)

# GEGLU.__init__ takes dim_in and dim_out
# GEGLU.forward takes x (a tensor)
# The forward method does:
#   - self.proj(x).chunk(2, dim=-1) - projects x and chunks along last dimension
#   - So x should have shape (batch, ..., dim_in)
#   - proj outputs (batch, ..., dim_out * 2)
#   - After chunk: two tensors of shape (batch, ..., dim_out)

dim_in = 4
dim_out = 3
batch_size = 2

# Create a small input tensor
x = torch.randn(batch_size, dim_in)

ARGS = {
    "dim_in": dim_in,
    "dim_out": dim_out,
}
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 GEGLU — 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 GEGLU 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
GroupNorm32 Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("426c2385fa431d9a")
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, GroupNorm32: 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)

class GroupNorm32(nn.GroupNorm):
    def forward(self, x):
        return super().forward(x.float()).type(x.dtype)

# GroupNorm32 inherits from nn.GroupNorm
# nn.GroupNorm.__init__ signature: GroupNorm(num_groups, num_channels, eps=1e-5, affine=True)
# The forward method takes a tensor x and processes it

# Create valid arguments
num_groups = 2
num_channels = 4
eps = 1e-5
affine = True

ARGS = {
    "num_groups": num_groups,
    "num_channels": num_channels,
    "eps": eps,
    "affine": affine
}
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 GroupNorm32 — 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 GroupNorm32 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
MemoryEfficientCrossAttention Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("77ce242242a53898")
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, MemoryEfficientCrossAttention: 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)

def exists(val):
    return val is not None

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

# Parameters for MemoryEfficientCrossAttention
query_dim = 512
context_dim = 512
heads = 8
dim_head = 64
dropout = 0.1

ARGS = {
    'query_dim': query_dim,
    'context_dim': context_dim,
    'heads': heads,
    'dim_head': dim_head,
    'dropout': dropout,
}
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 MemoryEfficientCrossAttention — 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 MemoryEfficientCrossAttention 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
QKVAttention Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("186bf0385ab93dad")
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, QKVAttention: 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 as th
import torch.nn as nn
import math
import numpy as np

th.manual_seed(0)

class MockModel(nn.Module):
    """Mock model with total_ops attribute for counting FLOPs"""
    def __init__(self):
        super().__init__()
        self.total_ops = th.DoubleTensor([0])
    
    def forward(self, x):
        return x

# Create a QKVAttention instance
n_heads = 2

# Create input tensor
# Shape: [batch_size x (3 * n_heads * ch) x length]
# Let's use batch_size=2, n_heads=2, ch=4, length=8
batch_size = 2
ch = 4
length = 8
width = 3 * n_heads * ch  # 3 * 2 * 4 = 24

qkv_input = th.randn(batch_size, width, length)

ARGS = {
    "n_heads": n_heads,
}
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 QKVAttention — 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 QKVAttention 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
QKVAttentionLegacy Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("8dd1080ff568f7f4")
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, QKVAttentionLegacy: 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
import math
import numpy as np

torch.manual_seed(0)

# Create a minimal QKVAttentionLegacy model
model = nn.Module()
model.total_ops = torch.DoubleTensor([0])

# Parameters for QKVAttentionLegacy.__init__
n_heads = 2

ARGS = {
    "n_heads": n_heads,
}
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 QKVAttentionLegacy — 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 QKVAttentionLegacy 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
Upsample Ran
ran on a synthesized input · constructed an object; no result was computed
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("1b4579fe4aec5257")
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, Upsample: 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 = {
    "channels": 4,
    "use_conv": True,
    "dims": 2,
    "out_channels": 8,
    "padding": 1,
}
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 Upsample — 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 Upsample 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
linear Ran
ran; our contract draft was wrong, not the code
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("0e30585f04efffbe")
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 Linear. 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 = {
    'in_features': 4,
    'out_features': 3,
    'bias': True,
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
normalization Ran
ran; our contract draft was wrong, not the code
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("daafc1c89511b8be")
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 GroupNorm32. 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 = {
    "channels": 64
}
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 GroupNorm32 — a GroupNorm32 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm32 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
project_to_subspaces Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
adobe-research/domain-expansion/expansion_utils/latent_operations.py
pointer only (licence: NOASSERTION) · get_code("3d6ab840977ec3fe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, adobe-research/domain-expansion (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.

timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("9df115707ad18735")
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 math

torch.manual_seed(0)

# Create a small batch of timestep indices
timesteps = torch.tensor([0, 5], dtype=torch.int64)

# Dimension for embedding output
dim = 4

# Max period parameter (default is 10000)
max_period = 10000

# Flag to control embedding behavior
repeat_only = False

ARGS = {
    "timesteps": timesteps,
    "dim": dim,
    "max_period": max_period,
    "repeat_only": repeat_only,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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
w_to_wplus Ran
ran; our contract draft was wrong, not the code
adobe-research/domain-expansion/expansion_utils/latent_operations.py
pointer only (licence: NOASSERTION) · get_code("68d7fb7e4dabea9b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, adobe-research/domain-expansion (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.

wplus_to_w Ran
ran; our contract draft was wrong, not the code
adobe-research/domain-expansion/expansion_utils/latent_operations.py
pointer only (licence: NOASSERTION) · get_code("813a9bbe55cbc6bc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, adobe-research/domain-expansion (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.

AttentionBlock Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("9ad1408b60f64d8e")
How it ran

no invocation recorded.

BasicTransformerBlock Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("76c528e8baaee5c6")
How it ran

no invocation recorded.

ControlNet Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("422ae8467d21d22b")
How it ran

no invocation recorded.

ResBlock Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("6ac534327b50ba98")
How it ran

no invocation recorded.

SpatialTransformer Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("9c960ef8abe48657")
How it ran

no invocation recorded.

TimestepBlock Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("7958a01675377ce4")
How it ran

no invocation recorded.

TimestepEmbedSequential Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("07137093faf869ca")
How it ran

no invocation recorded.

avg_pool_nd Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from andreasfloros/cascaded-wavelet-diffusion
pointer only · get_code("ecd0fc28815b65ae")
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. No invocation recorded.

checkpoint Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("c596e50230fd9ed8")
How it ran

no invocation recorded.

count_flops_attn Not yet run
unverified (harvested, no recorded run)
lllyasviel/controlnet/cldm/cldm.py
code served (permissive licence) · get_code("6e9c81a619f204c5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 23 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 8 the same month, 23 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
avg_pool_nd
brick of this paper's assembly: helper
113 other papers
27 dated earlier, 2 the same month, 83 later, 1 same year, order not determinable · 31 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 110 more not named here
checkpoint
brick of this paper's assembly: helper
51 other papers
5 dated earlier, 1 the same month, 45 later · 29 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 48 more not named here
linear
brick of this paper's assembly: helper
36 other papers
6 dated earlier, 1 the same month, 29 later · 35 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2103.11161 (2021-03)
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
2112.10741 (2021-12)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
and 33 more not named here
TimestepBlock
brick of this paper's assembly: helper
33 other papers
6 dated earlier, 1 the same month, 26 later · 28 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2112.10741 (2021-12)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
and 30 more not named here
normalization
brick of this paper's assembly: helper
32 other papers
3 dated earlier, 1 the same month, 28 later · 27 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
and 29 more not named here
GroupNorm32
brick of this paper's assembly: helper
31 other papers
3 dated earlier, 1 the same month, 27 later · 29 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
and 28 more not named here
timestep_embedding
brick of this paper's assembly: helper
25 other papers
1 dated earlier, 24 later · 8 only as an assembly brick
2202.06875 (2022-02)
Visual Acoustic Matching
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
2305.16283 (2023-05)
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
and 22 more not named here
GEGLU
brick of this paper's assembly: helper
21 other papers
1 dated earlier, 20 later · 18 only as an assembly brick
2211.05556 (2022-11)
Generating astronomical spectra from photometry with conditional diffusion models
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
2303.14412 (2023-03)
Freestyle Layout-to-Image Synthesis
and 18 more not named here
FeedForward
brick of this paper's assembly: helper
20 other papers
1 dated earlier, 19 later · 14 only as an assembly brick
2211.05556 (2022-11)
Generating astronomical spectra from photometry with conditional diffusion models
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
2303.14412 (2023-03)
Freestyle Layout-to-Image Synthesis
and 17 more not named here
count_flops_attn
brick of this paper's assembly: helper
19 other papers
2 dated earlier, 17 later · 18 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
and 16 more not named here
QKVAttention
brick of this paper's assembly: helper
17 other papers
2 dated earlier, 15 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
and 14 more not named here
QKVAttentionLegacy
brick of this paper's assembly: helper
15 other papers
2 dated earlier, 13 later · 6 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
and 12 more not named here
AttentionBlock
brick of this paper's assembly: helper
12 other papers
1 dated earlier, 11 later · 2 only as an assembly brick
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
and 9 more not named here
Downsample
brick of this paper's assembly: helper
12 other papers
1 the same month, 11 later · 10 only as an assembly brick
2301.13721 (2023-01)
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
and 9 more not named here
ResBlock
brick of this paper's assembly: helper
11 other papers
1 dated earlier, 10 later · 4 only as an assembly brick
2209.15264 (2022-09)
Diffusion-based Image Translation using Disentangled Style and Content Representation
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
2304.02012 (2023-04)
EGC: Image Generation and Classification via a Diffusion Energy-Based Model
and 8 more not named here
Upsample
brick of this paper's assembly: helper
11 other papers
1 the same month, 10 later · 10 only as an assembly brick
2301.13721 (2023-01)
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
2302.04304 (2023-02)
Q-Diffusion: Quantizing Diffusion Models
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
and 8 more not named here
TimestepEmbedSequential
brick of this paper's assembly: helper
8 other papers
8 later
2302.07685 (2023-02)
Video Probabilistic Diffusion Models in Projected Latent Space
2304.02012 (2023-04)
EGC: Image Generation and Classification via a Diffusion Energy-Based Model
2305.18259 (2023-05)
GlyphControl: Glyph Conditional Control for Visual Text Generation
and 5 more not named here
CheckpointFunction
brick of this paper's assembly: helper
4 other papers
4 later · 4 only as an assembly brick
2305.18259 (2023-05)
GlyphControl: Glyph Conditional Control for Visual Text Generation
2307.01097 (2023-07)
MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
2307.01952 (2023-07)
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
and 1 more not named here
BasicTransformerBlock
brick of this paper's assembly: helper
3 other papers
3 later
2305.18259 (2023-05)
GlyphControl: Glyph Conditional Control for Visual Text Generation
2404.11474 (2024-04)
Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt
2410.09400 (2024-10)
CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
SpatialTransformer
brick of this paper's assembly: helper
3 other papers
3 later
2305.18259 (2023-05)
GlyphControl: Glyph Conditional Control for Visual Text Generation
2404.11474 (2024-04)
Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt
2410.09400 (2024-10)
CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

Shown: the 20 functions present in the most other papers. 3 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

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

Abstract

Dormant direction Figure 1. (center) Traversing the latent space of generative models along some directions changes the image significantly while traversing others has no perceptible effect. We call such directions dormant. (left) Domain adaptation methods, transform the entire generator from a source domain to a target domain. (right) We introduce an approach for a new task -domain expansion. Rather than transforming the generator fully, we expand it to include new data domains. Our method learns to represent the new domain in a disentangled manner by repurposing a single dormant direction.

For agents

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

get_harvested_code_for_paper("2301.05225")
get_code_for_paper("2301.05225")
have("2301.05225")

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

curl https://syntology.ai/api/ran/2301.05225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.05225.svg)](https://syntology.ai/paper/2301.05225)

Connect an agent — have() is free.