SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.07093 · CVPR · 2023

GLIGEN: Open-Set Grounded Text-to-Image Generation

Chunyuan Li, Jianfeng Gao, Fangzhou Mu, Jianwei Yang, Haotian Liu, Yuheng Li, Qingyang Wu, Yong Jae Lee

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2301.07093.json · badge: /api/ran/2301.07093.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
gligen/GLIGEN marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
FourierEmbedder Ran
ran on a synthesized input · constructed an object; no result was computed
gligen/GLIGEN/ldm/modules/diffusionmodules/text_image_grounding_net.py
code served (permissive licence) · get_code("507c6b1494a9654d")
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, FourierEmbedder: 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

torch.manual_seed(0)

# FourierEmbedder has two __init__ parameters: num_freqs and temperature
# The __call__ method takes x (a tensor) and cat_dim (an int, default -1)

# For ARGS, we need to provide arguments to construct the FourierEmbedder instance
ARGS = {
    'num_freqs': 64,
    'temperature': 100
}

# Example of how to use it (not required, but shows validity):
# embedder = FourierEmbedder(**ARGS)
# x = torch.randn(2, 4)  # batch_size=2, feature_dim=4
# output = embedder(x, cat_dim=-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 FourierEmbedder — 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 FourierEmbedder 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
PositionNet Ran
ran on a synthesized input · constructed an object; no result was computed
gligen/GLIGEN/ldm/modules/diffusionmodules/text_image_grounding_net.py
code served (permissive licence) · get_code("ebf186a07a3f13ba")
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, PositionNet: 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)

# Define ARGS dict with all parameters for PositionNet.__init__
ARGS = {
    "in_dim": 8,
    "out_dim": 16,
    "fourier_freqs": 4,
}

# Verify the setup by instantiating the model
model = nn.Module.__new__(type('PositionNet', (nn.Module,), {}))
model.__dict__.update(ARGS)

# Now create actual forward pass test data
B = 2  # batch size
N = 3  # number of objects
in_dim = ARGS["in_dim"]
out_dim = ARGS["out_dim"]
fourier_freqs = ARGS["fourier_freqs"]
position_dim = fourier_freqs * 2 * 4

# Create forward pass arguments
boxes = torch.randn(B, N, 4)  # (B, N, 4) - bounding boxes with 4 coordinates
masks = torch.ones(B, N, dtype=torch.bool)  # (B, N) - object masks
text_masks = torch.ones(B, N, dtype=torch.bool)  # (B, N) - text masks
image_masks = torch.ones(B, N, dtype=torch.bool)  # (B, N) - image masks
text_embeddings = torch.randn(B, N, in_dim)  # (B, N, in_dim) - text features
image_embeddings = torch.randn(B, N, in_dim)  # (B, N, in_dim) - image features

# Add forward args to ARGS for completeness (optional, but useful)
ARGS_FORWARD = {
    "boxes": boxes,
    "masks": masks,
    "text_masks": text_masks,
    "image_masks": image_masks,
    "text_embeddings": text_embeddings,
    "image_embeddings": image_embeddings,
}

ARGS = {
    "in_dim": 8,
    "out_dim": 16,
    "fourier_freqs": 4,
}
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 PositionNet — 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 PositionNet 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
FourierEmbedder
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2402.05408 (2024-02)
MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
2605.31266 (2026-05)
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

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

https://gligen.github.io/ Caption: "A woman sitting in a restaurant with a pizza in front of her " Grounded text: table, pizza, person, wall, car, paper, chair, window, bottle, cup Caption: "a baby girl / monkey / Hormer Simpson / is scratching her/its head" Grounded keypoints: plotted dots on the left image Caption: "A dog / bird / helmet / backpack is on the grass" Grounded image: red inset Caption: "Elon Musk and Emma Watson on a movie poster" Grounded text: Elon Musk, Emma Watson; Grounded style image: blue inset Caption: "A vibrant colorful bird sitting on tree branch" Grounded depth map: the left image Caption: "A young boy with white powder on his face looks away" Grounded HED map: the left image Caption: "Cars park on the snowy street" Grounded normal map: the left image Caption: "A living room filled with lots of furniture and plants" Grounded semantic map: the left image § Part of the work performed at Microsoft; ¶ Co-senior authors This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.

For agents

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

get_harvested_code_for_paper("2301.07093")
get_code_for_paper("2301.07093")
have("2301.07093")

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

curl https://syntology.ai/api/ran/2301.07093.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.07093.svg)](https://syntology.ai/paper/2301.07093)

Connect an agent — have() is free.