SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.04410 · 2024

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 1 failure 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/2409.04410.json · badge: /api/ran/2409.04410.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
tencentarc/seed-voken canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
check_image Ran
ran, violated the contract we drafted
tencentarc/seed-voken/src/Open_MAGVIT2/data/prepare_pretrain.py
code served (permissive licence) · get_code("935e50ad10badd9b")
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.

from PIL import Image
import io

# Create a valid image in bytes format
# Create a simple 512x512 RGB image
img = Image.new('RGB', (512, 512), color='red')
img_bytes = io.BytesIO()
img.save(img_bytes, format='PNG')
image_data = img_bytes.getvalue()

ARGS = {
    'image_data': image_data,
    'filter': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL — 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
check_tar_file Ran
ran; our contract draft was wrong, not the code
tencentarc/seed-voken/src/Open_MAGVIT2/data/prepare_pretrain.py
code served (permissive licence) · get_code("d35f32440fc28b88")
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. 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 tarfile
import os
from PIL import Image
import io

# Create a temporary directory for test tar files
temp_dir = tempfile.mkdtemp()

# Create a simple test image in memory
def create_test_image(width=512, height=512):
    img = Image.new('RGB', (width, height), color='red')
    img_bytes = io.BytesIO()
    img.save(img_bytes, format='JPEG')
    return img_bytes.getvalue()

# Create test tar files with jpg images
tar_paths = []
for i in range(2):
    tar_path = os.path.join(temp_dir, f'test_{i}.tar')
    with tarfile.open(tar_path, 'w') as tar:
        # Add a valid jpg image
        image_data = create_test_image(512, 512)
        tarinfo = tarfile.TarInfo(name=f'image_{i}_1.jpg')
        tarinfo.size = len(image_data)
        tar.addfile(tarinfo, io.BytesIO(image_data))
        
        # Add another valid jpg image
        image_data2 = create_test_image(600, 600)
        tarinfo2 = tarfile.TarInfo(name=f'image_{i}_2.jpg')
        tarinfo2.size = len(image_data2)
        tar.addfile(tarinfo2, io.BytesIO(image_data2))
        
        # Add a non-jpg file (should be skipped)
        text_data = b'not an image'
        tarinfo3 = tarfile.TarInfo(name=f'readme_{i}.txt')
        tarinfo3.size = len(text_data)
        tar.addfile(tarinfo3, io.BytesIO(text_data))
    
    tar_paths.append(tar_path)

# Define arguments for check_tar_file function
ARGS = {
    'args': (tar_paths, 0, 1)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL — 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
disabled_train Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from zhouc20/LatentGraphDiffusion
pointer only · get_code("4cb732f513d69dfd")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 2 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
disabled_train 173 other papers
135 dated earlier, 3 the same month, 27 later, 8 same year, order not determinable · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 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 Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a super-large codebook (i.e., $2^{18}$ codes), and achieves the state-of-the-art reconstruction performance on ImageNet and UCF benchmarks. We also provide a tokenizer pre-trained on large-scale data, significantly outperforming Cosmos on zero-shot benchmarks (1.93 vs. 0.78 rFID on ImageNet original resolution). Furthermore, we explore its application in plain auto-regressive models to validate scalability properties, producing a family of auto-regressive image generation models ranging from 300M to 1.5B. To assist auto-regressive models in predicting with a super-large vocabulary, we factorize it into two sub-vocabulary of different sizes by asymmetric token factorization, and further introduce ``next sub-token prediction'' to enhance sub-token interaction for better generation quality. We release all models and codes to foster innovation and creativity in the field of auto-regressive visual generation.

For agents

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

get_harvested_code_for_paper("2409.04410")
get_code_for_paper("2409.04410")
have("2409.04410")

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

curl https://syntology.ai/api/ran/2409.04410.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.04410.svg)](https://syntology.ai/paper/2409.04410)

Connect an agent — have() is free.