SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.05511 · CVPR · 2023

Scaling up GANs for Text-to-Image Synthesis

Sylvain Paris, Jaesik Park, Richard Zhang, Minguk Kang, Taesung Park, Jun-Yan Zhu, Eli Shechtman, Postech

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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, 3 violated it and 4 have no contract verdict; 4 failures of our instrument; 2 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/2303.05511.json · badge: /api/ran/2303.05511.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
lucidrains/gigagan-pytorch community (classifier label)
classifier basis not recorded on the link
12 ran · 2 no recorded run
FunctionStatusWhere it lives
cast_tuple Ran
ran, honoured the contract we drafted
lucidrains/gigagan-pytorch/gigagan_pytorch/gigagan_pytorch.py
code served (permissive licence) · get_code("c1b68cdd9e73316a")
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 tuple, 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 torch

torch.manual_seed(0)

ARGS = {
    "t": 42,
    "length": 3
}
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 tuple, ndim 1, dtype family int — 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
collate_tensors_or_str Ran
ran on a synthesized input
lucidrains/gigagan-pytorch/gigagan_pytorch/data.py
code served (permissive licence) · get_code("e00d99c5c034f0cf")
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 tuple. 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 beartype.door import is_bearable
from beartype.typing import Tuple

torch.manual_seed(0)

# Test case 1: single tensors (is_one_data = True)
data_single = [torch.randn(4), torch.randn(4), torch.randn(4)]

# Test case 2: tuples of tensors and strings (is_one_data = False)
data_mixed = [
    (torch.randn(3), "label_a"),
    (torch.randn(3), "label_b"),
]

ARGS = {
    "data": data_mixed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
convert_image_to_fn Ran
ran on a synthesized input
lucidrains/gigagan-pytorch/gigagan_pytorch/data.py
code served (permissive licence) · get_code("de4083f9d5bd078a")
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 Image. 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.

from PIL import Image

# Create a small PIL Image object
img = Image.new('RGB', (2, 2), color='red')

# Create another image in a different mode for testing
img_la = Image.new('LA', (2, 2), color=(255, 128))

ARGS = {
    'img_type': 'LA',
    'image': img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
default Ran
ran, violated the contract we drafted
lucidrains/gigagan-pytorch/gigagan_pytorch/unet_upsampler.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
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 str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

# Test case 1: val is not None, should return val
val_1 = "test_value"
d_1 = lambda: "default_value"

# Test case 2: val is None, d is callable, should return d()
val_2 = None
d_2 = lambda: "computed_default"

# Test case 3: val is None, d is not callable, should return d
val_3 = None
d_3 = "static_default"

# Test case 4: val is a number
val_4 = 42
d_4 = 100

# Test case 5: val is a tensor
val_5 = torch.tensor([1.0, 2.0, 3.0])
d_5 = lambda: torch.tensor([0.0])

ARGS = {
    "val": val_1,
    "d": d_1
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
exists Ran
ran, violated the contract we drafted
lucidrains/gigagan-pytorch/gigagan_pytorch/attend.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.

exists Ran
ran, violated the contract we drafted
lucidrains/gigagan-pytorch/gigagan_pytorch/unet_upsampler.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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 bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
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 bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_optimizer Ran
ran on a synthesized input
lucidrains/gigagan-pytorch/gigagan_pytorch/optimizer.py
code served (permissive licence) · get_code("7a7729a2c6a2adee")
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 AdamW. 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.optim import AdamW, Adam

torch.manual_seed(0)

# Create a simple model to generate parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # Create parameters with different dimensions
        # 2D parameters (weight-decay-able)
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        # 1D parameters (no weight decay)
        self.bias_only = nn.Parameter(torch.randn(2))
        # 0D parameter (no weight decay)
        self.scalar = nn.Parameter(torch.tensor(0.5))

model = SimpleModel()

# Extract parameters from model
params = list(model.parameters())

# Ensure all parameters require gradients
for param in params:
    param.requires_grad = True

# Define ARGS with all parameters of get_optimizer
ARGS = {
    'params': params,
    'lr': 0.0001,
    'wd': 0.01,
    'betas': (0.9, 0.99),
    'eps': 1e-08,
    'filter_by_requires_grad': True,
    'group_wd_params': 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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_empty Ran
ran on a synthesized input
lucidrains/gigagan-pytorch/gigagan_pytorch/gigagan_pytorch.py
code served (permissive licence) · get_code("2c9c110bdde8a564")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from collections.abc import Iterable

torch.manual_seed(0)

# The function is_empty takes an Iterable and checks if len(arr) == 0
# We need to provide an argument that is an Iterable and supports len()

# Test with a non-empty list
arr_non_empty = [1, 2, 3, 4]

# Test with an empty list
arr_empty = []

# Test with a tensor
tensor_non_empty = torch.randn(2, 4)

# Test with a tuple
tuple_empty = ()

# We'll use a non-empty list as the primary test case
ARGS = {
    "arr": arr_non_empty
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l2norm Ran
ran; our contract draft was wrong, not the code
lucidrains/gigagan-pytorch/gigagan_pytorch/open_clip.py
pointer only (licence: MIT); the stored copy get_code serves, from tmlresearchgroup-cas/clipure, is pointer only (licence: NONE) · get_code("3eb58dae620046d3")
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 tmlresearchgroup-cas/clipure, 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.

once Ran
ran; our contract draft was wrong, not the code
lucidrains/gigagan-pytorch/gigagan_pytorch/attend.py
code served (permissive licence) · get_code("52e10a7d6b0fa036")
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
from functools import wraps

def once(fn):
    called = False

    @wraps(fn)
    def inner(x):
        nonlocal called
        if called:
            return
        called = True
        return fn(x)
    return inner


def sample_function(x):
    """A simple function that the decorator will wrap."""
    return x * 2


ARGS = {
    "fn": sample_function
}
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
pad_dim_to Ran
ran; our contract draft was wrong, not the code
lucidrains/gigagan-pytorch/gigagan_pytorch/distributed.py
code served (permissive licence) · get_code("d3d5bf1b20109dcd")
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 (5, 4, 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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor with distinct dimensions for probing
t = torch.randn(2, 4, 3)

# Set parameters
length = 5
dim = 0

ARGS = {
    "t": t,
    "length": length,
    "dim": dim,
}
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 (5, 4, 3) — shape (5, 4, 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
separate_weight_decayable_params Ran
ran; our contract draft was wrong, not the code
lucidrains/gigagan-pytorch/gigagan_pytorch/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from levyisthebest/echopulse_prelease, is pointer only (licence: NONE) · get_code("fdc11aefc97f3abb")
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 levyisthebest/echopulse_prelease, 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.

all_gather_variable_dim Not yet run
unverified (harvested, no recorded run)
lucidrains/gigagan-pytorch/gigagan_pytorch/distributed.py
code served (permissive licence) · get_code("556c3caa2d064c32")
How it ran

no invocation recorded.

pack_one Not yet run
unverified (harvested, no recorded run)
lucidrains/gigagan-pytorch/gigagan_pytorch/unet_upsampler.py
code served (permissive licence) · get_code("86ca4a3f9ab20a35")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 4 the same month, 9 later) and 5 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
150 dated earlier, 15 the same month, 315 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
exists 144 other papers
31 dated earlier, 3 the same month, 109 later, 1 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
default 79 other papers
12 dated earlier, 3 the same month, 64 later · 15 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
and 76 more not named here
once 19 other papers
7 dated earlier, 12 later · 4 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2203.07852 (2022-03)
Block-Recurrent Transformers
and 16 more not named here
l2norm 16 other papers
6 dated earlier, 1 the same month, 9 later · 4 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.07852 (2022-03)
Block-Recurrent Transformers
and 13 more not named here
pack_one 16 other papers
5 dated earlier, 11 later · 4 only as an assembly brick
2203.07852 (2022-03)
Block-Recurrent Transformers
2205.14135 (2022-05)
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
2206.11990 (2022-06)
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
and 13 more not named here
separate_weight_decayable_params 8 other papers
3 dated earlier, 5 later
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2301.11325 (2023-01)
MusicLM: Generating Music From Text
2302.04761 (2023-02)
Toolformer: Language Models Can Teach Themselves to Use Tools
and 5 more not named here
pad_dim_to 5 other papers
2 dated earlier, 3 later · 1 only as an assembly brick
2204.02311 (2022-04)
PaLM: Scaling Language Modeling with Pathways
2212.00794 (2022-12)
Scaling Language-Image Pre-training via Masking
2308.00951 (2023-08)
From Sparse to Soft Mixtures of Experts
and 2 more not named here
cast_tuple 4 other papers
1 dated earlier, 3 later
2203.07852 (2022-03)
Block-Recurrent Transformers
2403.10266 (2024-03)
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
2412.00733 (2024-12)
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

The recent success of text-to-image synthesis has taken the world by storm and captured the general public's imagination. From a technical standpoint, it also marked a drastic change in the favored architecture to design generative image models. GANs used to be the de facto choice, with techniques like StyleGAN. With DALL•E 2, autoregressive and diffusion models became the new standard for largescale generative models overnight. This rapid shift raises a fundamental question: can we scale up GANs to benefit from large datasets like LAION? We find that naïvely increasing the capacity of the StyleGAN architecture quickly becomes unstable. We introduce GigaGAN, a new GAN architecture that far exceeds this limit, demonstrating GANs as a viable option for text-to-image synthesis. GigaGAN offers three major advantages. First, it is orders of magnitude faster at inference time, taking only 0.13 seconds to synthesize a 512px image. Second, it can synthesize high-resolution images, for example, 16-megapixel images in 3.66 seconds. Finally, GigaGAN supports various latent space editing applications such as latent interpolation, style mixing, and vector arithmetic operations.

For agents

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

get_harvested_code_for_paper("2303.05511")
get_code_for_paper("2303.05511")
have("2303.05511")

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

curl https://syntology.ai/api/ran/2303.05511.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.05511.svg)](https://syntology.ai/paper/2303.05511)

Connect an agent — have() is free.