SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.11340 · 2024

OmniGen: Unified Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2409.11340.json · badge: /api/ran/2409.11340.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
vectorspacelab/omnigen canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
center_crop_arr Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/utils.py
code served (permissive licence) · get_code("ea73360d2d5d9224")
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 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
import numpy as np

# Create a simple PIL Image for testing
# Make it larger than 2 * image_size so we can test the resizing logic
pil_image = Image.new('RGB', (256, 256), color='red')

# Define image_size parameter
image_size = 64

# Construct ARGS dictionary
ARGS = {
    'pil_image': pil_image,
    'image_size': image_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — 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
create_logger Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/utils.py
code served (permissive licence) · get_code("b2cc78f4103df806")
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 Logger. 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 tempfile
import os

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

ARGS = {
    "logging_dir": temp_dir
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
crop_arr Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/utils.py
code served (permissive licence) · get_code("0deb02748179c848")
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
import numpy as np

# Create a simple PIL Image for testing
# Make it with dimensions that are not multiples of 16 to test the cropping logic
pil_image = Image.new('RGB', (256, 192), color='red')

max_image_size = 128

ARGS = {
    'pil_image': pil_image,
    'max_image_size': max_image_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
vectorspacelab/omnigen/OmniGen/model.py
code served (permissive licence) · get_code("b9da3bec8fc652d6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (16, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": False,
    "extra_tokens": 0,
    "interpolation_scale": 1.0,
    "base_size": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 (16, 8) — shape (16, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
modulate Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/model.py
code served (permissive licence) · get_code("03310bba324ae4fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sample_timestep Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/train_helper/loss.py
code served (permissive licence) · get_code("960d3e8d782a3a71")
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 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects x1 to be a sequence (has len()) where x1[0] is a tensor with a device attribute
# x1 should be a list of tensors
x1 = [
    torch.randn(4, 3),
    torch.randn(4, 3),
]

ARGS = {
    "x1": x1,
}
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 1, dtype family float, shape (2,) — shape (2,) 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
sample_x0 Ran
ran; our contract draft was wrong, not the code
vectorspacelab/omnigen/OmniGen/train_helper/loss.py
code served (permissive licence) · get_code("3aee916a58a0f3c2")
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

torch.manual_seed(0)

# Test case 1: x1 is a single tensor
x1_single = torch.randn(2, 4)

# Test case 2: x1 is a list of tensors
x1_list = [torch.randn(2, 4), torch.randn(2, 3)]

# Test case 3: x1 is a tuple of tensors
x1_tuple = (torch.randn(2, 4), torch.randn(2, 5))

# Use the single tensor case as the primary argument
ARGS = {
    "x1": x1_single
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
training_losses Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vectorspacelab/omnigen/OmniGen/train_helper/loss.py
code served (permissive licence) · get_code("bc251f0fab494c0d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. 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 DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, xt, t, **kwargs):
        # xt is [batch, 4], t is [batch]
        # Model outputs same shape as input
        batch_size = xt.shape[0]
        return self.linear(xt)

model = DummyModel()

# Create x1 as a simple tensor [batch=2, dim=4]
x1 = torch.randn(2, 4)

# model_kwargs as empty dict
model_kwargs = {}

# snr_type parameter
snr_type = 'uniform'

# patch_weight as None (or could be a tensor matching x1 shape)
patch_weight = None

ARGS = {
    'model': model,
    'x1': x1,
    'model_kwargs': model_kwargs,
    'snr_type': snr_type,
    'patch_weight': patch_weight
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
vectorspacelab/omnigen/OmniGen/model.py
code served (permissive licence) · get_code("665d8a4e8f673a4c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 4 the same month, 9 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
get_2d_sincos_pos_embed_from_grid 190 other papers
111 dated earlier, 8 the same month, 70 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
modulate 101 other papers
43 dated earlier, 5 the same month, 52 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
and 98 more not named here
center_crop_arr 37 other papers
11 dated earlier, 2 the same month, 24 later
2211.17091 (2022-11)
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2311.09257 (2023-11)
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
and 34 more not named here
create_logger 8 other papers
1 dated earlier, 2 the same month, 5 later
2311.09257 (2023-11)
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
2409.07756 (2024-09)
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing
2409.10695 (2024-09)
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models
and 5 more not named here
crop_arr 1 other paper
1 later
Xiao_OmniGen_Unified_Image_Generation_CVPR_2025_paper (2025 (year only))
OmniGen: Unified Image Generation
get_2d_sincos_pos_embed 1 other paper
1 later
Xiao_OmniGen_Unified_Image_Generation_CVPR_2025_paper (2025 (year only))
OmniGen: Unified Image Generation
sample_timestep 1 other paper
1 later
Xiao_OmniGen_Unified_Image_Generation_CVPR_2025_paper (2025 (year only))
OmniGen: Unified Image Generation
sample_x0 1 other paper
1 later
Xiao_OmniGen_Unified_Image_Generation_CVPR_2025_paper (2025 (year only))
OmniGen: Unified Image Generation
training_losses 1 other paper
1 later
Xiao_OmniGen_Unified_Image_Generation_CVPR_2025_paper (2025 (year only))
OmniGen: Unified 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

The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual-conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model's reasoning capabilities and potential applications of the chain-of-thought mechanism. This work represents the first attempt at a general-purpose image generation model, and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.

For agents

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

get_harvested_code_for_paper("2409.11340")
get_code_for_paper("2409.11340")
have("2409.11340")

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

curl https://syntology.ai/api/ran/2409.11340.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.11340.svg)](https://syntology.ai/paper/2409.11340)

Connect an agent — have() is free.