SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.00273 · 2022

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

arXiv · PDF · Open in the Atlas

Code that ran

16 of 19 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 3 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/2202.00273.json · badge: /api/ran/2202.00273.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
autonomousvision/stylegan_xl canonical (classifier label)
classifier basis: plan_row
16 ran · 3 no recorded run
FunctionStatusWhere it lives
parse_tuple Ran
ran, honoured the contract we drafted
autonomousvision/stylegan_xl/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("9cd07419f7c926f8")
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 pdillis/stylegan3-fun, 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.

NormLayer Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/pg_modules/blocks.py
code served (permissive licence) · get_code("ef1e7dffb5d433d4")
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 BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'c': 16,
    'mode': 'batch'
}
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 BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d 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
UpBlockBig Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/pg_modules/blocks.py
code served (permissive licence) · get_code("f87cd99314206f72")
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 torch.nn.utils import spectral_norm

torch.manual_seed(0)

def conv2d(*args, **kwargs):
    return spectral_norm(nn.Conv2d(*args, **kwargs))

def NormLayer(c, mode='batch'):
    if mode == 'group':
        return nn.GroupNorm(c // 2, c)
    elif mode == 'batch':
        return nn.BatchNorm2d(c)

class GLU(nn.Module):

    def forward(self, x):
        nc = x.size(1)
        assert nc % 2 == 0, 'channels dont divide 2!'
        nc = int(nc / 2)
        return x[:, :nc] * torch.sigmoid(x[:, nc:])

class NoiseInjection(nn.Module):

    def __init__(self):
        super().__init__()
        self.weight = nn.Parameter(torch.zeros(1), requires_grad=True)

    def forward(self, feat, noise=None):
        if noise is None:
            batch, _, height, width = feat.shape
            noise = torch.randn(batch, 1, height, width).to(feat.device)
        return feat + self.weight * noise

def UpBlockBig(in_planes, out_planes):
    block = nn.Sequential(nn.Upsample(scale_factor=2, mode='nearest'), conv2d(in_planes, out_planes * 2, 3, 1, 1, bias=False), NoiseInjection(), NormLayer(out_planes * 2), GLU(), conv2d(out_planes, out_planes * 2, 3, 1, 1, bias=False), NoiseInjection(), NormLayer(out_planes * 2), GLU())
    return block

ARGS = {
    'in_planes': 4,
    'out_planes': 8,
}
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
UpBlockSmall Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/pg_modules/blocks.py
code served (permissive licence) · get_code("0186912dcb8b92b9")
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 torch.nn.utils import spectral_norm

torch.manual_seed(0)

def conv2d(*args, **kwargs):
    return spectral_norm(nn.Conv2d(*args, **kwargs))

def NormLayer(c, mode='batch'):
    if mode == 'group':
        return nn.GroupNorm(c // 2, c)
    elif mode == 'batch':
        return nn.BatchNorm2d(c)

class GLU(nn.Module):

    def forward(self, x):
        nc = x.size(1)
        assert nc % 2 == 0, 'channels dont divide 2!'
        nc = int(nc / 2)
        return x[:, :nc] * torch.sigmoid(x[:, nc:])

def UpBlockSmall(in_planes, out_planes):
    block = nn.Sequential(nn.Upsample(scale_factor=2, mode='nearest'), conv2d(in_planes, out_planes * 2, 3, 1, 1, bias=False), NormLayer(out_planes * 2), GLU())
    return block

ARGS = {
    'in_planes': 4,
    'out_planes': 8
}
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
file_ext Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("a2b45afa097b55b6")
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 pdillis/stylegan3-fun, 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.

format_time Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/dnnlib/util.py
pointer only (licence: MIT); the stored copy get_code serves, from ntuaislab/DRAG, is pointer only (licence: NOASSERTION) · get_code("053fc534bc6bb989")
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 ntuaislab/DRAG, 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.

format_time_brief Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/dnnlib/util.py
pointer only (licence: MIT); the stored copy get_code serves, from ntuaislab/DRAG, is pointer only (licence: NOASSERTION) · get_code("77f4aa0649e7f404")
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 ntuaislab/DRAG, 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.

forward_flex Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/stylegan_xl/feature_networks/vit.py
code served (permissive licence) · get_code("562cccfa5027f008")
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 3, dtype family float, shape (2, 17, 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)

# Create a minimal Vision Transformer-like model
class MinimalPatchEmbed(nn.Module):
    def __init__(self, in_channels=3, embed_dim=4, patch_size=16):
        super().__init__()
        self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size)
    
    def forward(self, x):
        return self.proj(x)

class MinimalTransformerBlock(nn.Module):
    def __init__(self, dim=4):
        super().__init__()
        self.norm1 = nn.LayerNorm(dim)
        self.attn = nn.Linear(dim, dim)
        self.norm2 = nn.LayerNorm(dim)
        self.mlp = nn.Linear(dim, dim)
    
    def forward(self, x):
        x = x + self.attn(self.norm1(x))
        x = x + self.mlp(self.norm2(x))
        return x

class MinimalVisionTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.patch_size = (16, 16)  # (height_patch_size, width_patch_size)
        
        # Patch embedding
        self.patch_embed = MinimalPatchEmbed(in_channels=3, embed_dim=4, patch_size=16)
        
        # Class token
        self.cls_token = nn.Parameter(torch.randn(1, 1, 4))
        
        # Positional embedding - initialize for a specific size
        # For input 64x64 with patch_size 16: we get 4x4 patches = 16 tokens
        self.pos_embed = nn.Parameter(torch.randn(1, 17, 4))  # 1 cls + 16 patches
        
        # Distance token (optional)
        self.dist_token = None
        
        # Dropout
        self.pos_drop = nn.Dropout(p=0.0)
        
        # Transformer blocks
        self.blocks = nn.ModuleList([MinimalTransformerBlock(dim=4) for _ in range(2)])
        
        # Norm layer
        self.norm = nn.LayerNorm(4)
    
    def _resize_pos_embed(self, pos_embed, h, w):
        # Simple implementation: just return pos_embed reshaped or interpolated
        # For this test, return pos_embed as-is if size matches, else interpolate
        num_patches = h * w + 1  # +1 for cls token
        if pos_embed.shape[1] == num_patches:
            return pos_embed
        # Simple resize by repetition for minimal case
        return pos_embed[:, :num_patches, :]
    
    def forward_flex(self, x):
        b, c, h, w = x.shape
        pos_embed = self._resize_pos_embed(self.pos_embed, h // self.patch_size[1], w // self.patch_size[0])
        B = x.shape[0]
        if hasattr(self.patch_embed, 'backbone'):
            x = self.patch_embed.backbone(x)
            if isinstance(x, (list, tuple)):
                x = x[-1]
        x = self.patch_embed.proj(x).flatten(2).transpose(1, 2)
        if hasattr(self, 'dist_token') and self.dist_token is not None:
            cls_tokens = self.cls_token.expand(B, -1, -1)
            dist_token = self.dist_token.expand(B, -1, -1)
            x = torch.cat((cls_tokens, dist_token, x), dim=1)
        else:
            cls_tokens = self.cls_token.expand(B, -1, -1)
            x = torch.cat((cls_tokens, x), dim=1)
        x = x + pos_embed
        x = self.pos_drop(x)
        for blk in self.blocks:
            x = blk(x)
        x = self.norm(x)
        return x

model = MinimalVisionTransformer()

# Create input tensor: batch_size=2, channels=3, height=64, width=64
x = torch.randn(2, 3, 64, 64)

ARGS = {
    'self': model,
    '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 Tensor, ndim 3, dtype family float, shape (2, 17, 4) — shape (2, 17, 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_activation Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/feature_networks/vit.py
code served (permissive licence) · get_code("1c094193a4506a40")
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 function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function get_activation takes a single parameter: name
# It returns a hook function that captures activations by name
# The hook function itself takes (model, input, output) but we only need to
# construct arguments for get_activation, which just needs a name string

ARGS = {
    "name": "layer_output"
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
layout_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/stylegan_xl/gen_video.py
code served (permissive licence) · get_code("456c172851946697")
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 ndarray, ndim 3, dtype family int, shape (4, 10, 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

torch.manual_seed(0)

# Create a small batch of images
# batch_size=2, channels=3, height=4, width=5
img = torch.randn(2, 3, 4, 5)

# Normalize to roughly [-1, 1] range for float_to_uint8 conversion
img = img / 10.0

ARGS = {
    "img": img,
    "grid_w": None,
    "grid_h": 1,
    "float_to_uint8": True,
    "chw_to_hwc": True,
    "to_numpy": 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 ndarray, ndim 3, dtype family int, shape (4, 10, 3) — shape (4, 10, 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
make_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/stylegan_xl/gen_images.py
code served (permissive licence) · get_code("f47dff4b7b27bba7")
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 ndarray, ndim 2, dtype family float, shape (3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "translate": (1.5, 2.5),
    "angle": 45.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (3, 3) — shape (3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
maybe_min Ran
ran, honoured the contract we drafted
autonomousvision/stylegan_xl/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("dd1dc700e87f36cc")
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 pdillis/stylegan3-fun, 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.

parse_comma_separated_list Ran
ran; our contract draft was wrong, not the code
autonomousvision/stylegan_xl/calc_metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from nv-tlabs/GET3D, is pointer only (licence: NOASSERTION) · get_code("d01b68a634f71551")
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 nv-tlabs/GET3D, 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.

parse_range Ran
ran, honoured the contract we drafted
autonomousvision/stylegan_xl/gen_images.py
code served (permissive licence) · get_code("236de8614a178382")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 re
from typing import List, Optional, Tuple, Union

def parse_range(s: Union[str, List]) -> List[int]:
    """Parse a comma separated list of numbers or ranges and return a list of ints.

    Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
    """
    if isinstance(s, list):
        return s
    ranges = []
    range_re = re.compile('^(\\d+)-(\\d+)$')
    for p in s.split(','):
        m = range_re.match(p)
        if m:
            ranges.extend(range(int(m.group(1)), int(m.group(2)) + 1))
        else:
            ranges.append(int(p))
    return ranges


# Test case 1: string with ranges and individual numbers
ARGS = {
    "s": "1,2,5-10"
}
Setup block drafted by
a language model, Claude Haiku 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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
parse_range Ran
ran, honoured the contract we drafted
autonomousvision/stylegan_xl/gen_video.py
code served (permissive licence) · get_code("025e4c7cda618f25")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 re
from typing import List, Optional, Tuple, Union

def parse_range(s: Union[str, List[int]]) -> List[int]:
    """Parse a comma separated list of numbers or ranges and return a list of ints.

    Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
    """
    if isinstance(s, list):
        return s
    ranges = []
    range_re = re.compile('^(\\d+)-(\\d+)$')
    for p in s.split(','):
        m = range_re.match(p)
        if m:
            ranges.extend(range(int(m.group(1)), int(m.group(2)) + 1))
        else:
            ranges.append(int(p))
    return ranges


# Test with string input
ARGS = {
    "s": "1,2,5-10"
}
Setup block drafted by
a language model, Claude Haiku 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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
parse_vec2 Ran
ran, honoured the contract we drafted
autonomousvision/stylegan_xl/gen_images.py
code served (permissive licence) · get_code("180016b9227381b1")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 typing import Union, Tuple

torch.manual_seed(0)

# The function parse_vec2 takes a single parameter 's' which can be either:
# - a string in format 'a,b' (e.g., '0,1')
# - a tuple of two floats (e.g., (0.0, 1.0))
# 
# The function either returns the tuple directly if input is tuple,
# or parses the string and returns a tuple of floats.

# Test case 1: string input
test_string = "0.5,1.5"

# Test case 2: tuple input
test_tuple = (2.0, 3.5)

# We'll use the string case as the primary test
ARGS = {
    "s": "0.5,1.5"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
ask_yes_no Not yet run
unverified (harvested, no recorded run)
autonomousvision/stylegan_xl/dnnlib/util.py
code served (permissive licence) · get_code("9d31d2c4cd16bb2d")
How it ran

no invocation recorded.

compute_is Not yet run
unverified (harvested, no recorded run)
autonomousvision/stylegan_xl/metrics/inception_score.py
pointer only (licence: MIT); the stored copy get_code serves, from hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, is pointer only (licence: NONE) · get_code("fc49fa553c005268")
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 hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, 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.

forward_vit Not yet run
unverified (harvested, no recorded run)
autonomousvision/stylegan_xl/feature_networks/vit.py
code served (permissive licence) · get_code("4c52162336ee4320")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 19 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 0 the same month, 19 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
format_time 73 other papers
3 dated earlier, 69 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
3 dated earlier, 65 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
format_time_brief 68 other papers
1 dated earlier, 66 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
2303.10137 (2023-03)
A Recipe for Watermarking Diffusion Models
and 65 more not named here
file_ext 35 other papers
4 dated earlier, 31 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
maybe_min 35 other papers
4 dated earlier, 31 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
parse_comma_separated_list 13 other papers
1 dated earlier, 12 later
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
2209.11163 (2022-09)
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
and 10 more not named here
parse_vec2 11 other papers
2 dated earlier, 9 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 8 more not named here
get_activation 10 other papers
1 dated earlier, 9 later · 1 only as an assembly brick
2103.13413 (2021-03)
Vision Transformers for Dense Prediction
2210.01035 (2022-10)
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
2303.16890 (2023-03)
DPF: Learning Dense Prediction Fields with Weak Supervision
and 7 more not named here
parse_range 9 other papers
1 dated earlier, 8 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
2212.09877 (2022-12)
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
and 6 more not named here
make_transform 8 other papers
2 dated earlier, 6 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2303.13071 (2023-03)
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
and 5 more not named here
parse_tuple 7 other papers
1 dated earlier, 6 later
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
and 4 more not named here
NormLayer 6 other papers
1 dated earlier, 5 later
2111.01007 (2021-11)
Projected GANs Converge Faster
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2310.02279 (2023-10)
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
and 3 more not named here
layout_grid 6 other papers
6 later
2211.11208 (2022-11)
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
2303.13071 (2023-03)
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
and 3 more not named here
UpBlockBig 5 other papers
5 later
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2310.02279 (2023-10)
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
2405.14822 (2024-05)
PaGoDA : Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
and 2 more not named here
UpBlockSmall 5 other papers
5 later
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2310.02279 (2023-10)
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
2405.14822 (2024-05)
PaGoDA : Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
and 2 more not named here
compute_is 5 other papers
5 later
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2311.08403 (2023-11)
Instant3D: Instant Text-to-3D Generation
2311.17857 (2023-11)
Gaussian Shell Maps for Efficient 3D Human Generation
and 2 more not named here
forward_flex 4 other papers
4 later
2310.02279 (2023-10)
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
2405.14822 (2024-05)
PaGoDA : Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
2502.06349 (2025-02)
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
and 1 more not named here
forward_vit 4 other papers
4 later
2310.02279 (2023-10)
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
2405.14822 (2024-05)
PaGoDA : Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
2502.06349 (2025-02)
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
and 1 more not named here
parse_range 3 other papers
3 later
2303.13071 (2023-03)
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2502.06349 (2025-02)
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead

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

Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN's performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected GAN paradigm, we leverage powerful neural network priors and a progressive growing strategy to successfully train the latest StyleGAN3 generator on ImageNet. Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of $1024^2$ at such a dataset scale. We demonstrate that this model can invert and edit images beyond the narrow domain of portraits or specific object classes.

For agents

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

get_harvested_code_for_paper("2202.00273")
get_code_for_paper("2202.00273")
have("2202.00273")

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

curl https://syntology.ai/api/ran/2202.00273.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.00273.svg)](https://syntology.ai/paper/2202.00273)

Connect an agent — have() is free.