SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.08453 · 2025

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 3 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/2501.08453.json · badge: /api/ran/2501.08453.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
Vchitect/Vchitect-2.0 community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
images_to_gif_bytes Ran
ran on a synthesized input
Vchitect/Vchitect-2.0/utils.py
code served (permissive licence) · get_code("43bd88e3a641a3b8")
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 bytes. 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 small test images
def create_test_image(size=(4, 3), color=(255, 0, 0)):
    """Create a simple PIL Image with given size and color."""
    array = np.full((*size, 3), color, dtype=np.uint8)
    return Image.fromarray(array)

# Create a list of images for the GIF
images = [
    create_test_image((4, 3), (255, 0, 0)),
    create_test_image((4, 3), (0, 255, 0)),
    create_test_image((4, 3), (0, 0, 255)),
]

ARGS = {
    "images": images,
    "duration": 500,
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
load_text_encoders Ran
ran on a synthesized input
Vchitect/Vchitect-2.0/models/pipeline.py
code served (permissive licence) · get_code("0aa26c53aa23a0b2")
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 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 torch.nn as nn
from unittest.mock import MagicMock, patch

torch.manual_seed(0)

# Create mock classes that mimic HuggingFace model classes
class MockTextEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    @classmethod
    def from_pretrained(cls, load_path, subfolder=None, revision=None, variant=None):
        """Mock from_pretrained that returns an instance"""
        return cls()

class MockClassOne(MockTextEncoder):
    pass

class MockClassTwo(MockTextEncoder):
    pass

class MockClassThree(MockTextEncoder):
    pass

ARGS = {
    'load_path': '/mock/model/path',
    'class_one': MockClassOne,
    'class_two': MockClassTwo,
    'class_three': MockClassThree,
    'precision': 'fp16'
}
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 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
replace_all_groupnorms Ran
ran on a synthesized input
Vchitect/Vchitect-2.0/op_replace.py
code served (permissive licence) · get_code("16b3184e0f465c5a")
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 SimpleModelWithGroupNorm. 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)

# Create a model with GroupNorm layers at various depths
class SimpleModelWithGroupNorm(nn.Module):
    def __init__(self):
        super().__init__()
        self.gn1 = nn.GroupNorm(num_groups=2, num_channels=4)
        self.conv1 = nn.Conv2d(4, 8, kernel_size=3)
        self.gn2 = nn.GroupNorm(num_groups=2, num_channels=8)
        self.nested = nn.Sequential(
            nn.GroupNorm(num_groups=4, num_channels=16),
            nn.Linear(16, 8)
        )
    
    def forward(self, x):
        return x

model = SimpleModelWithGroupNorm()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
apex, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModelWithGroupNorm — a SimpleModelWithGroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModelWithGroupNorm 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
retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
Vchitect/Vchitect-2.0/models/pipeline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from krafton-ai/Rare-to-Frequent, is pointer only (licence: NONE) · get_code("0b56680ee1708fee")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from krafton-ai/Rare-to-Frequent, 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.

images_to_mp4_bytes Not yet run
unverified (harvested, no recorded run)
Vchitect/Vchitect-2.0/utils.py
code served (permissive licence) · get_code("180e02163f8eb159")
How it ran

no invocation recorded.

load_tf_weights_in_t5 Not yet run
unverified (harvested, no recorded run)
Vchitect/Vchitect-2.0/models/modeling_t5.py
code served (permissive licence) · get_code("f383d81f62012649")
How it ran

no invocation recorded.

replace_all_layernorms Not yet run
unverified (harvested, no recorded run)
Vchitect/Vchitect-2.0/op_replace.py
code served (permissive licence) · get_code("fcac3c3ec02cb5c9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 6 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
retrieve_timesteps 46 other papers
14 dated earlier, 2 the same month, 27 later, 1 same year, order not determinable, 2 undated
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2402.10491 (2024-02)
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
2405.18991 (2024-05)
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
and 43 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

We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.

For agents

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

get_harvested_code_for_paper("2501.08453")
get_code_for_paper("2501.08453")
have("2501.08453")

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

curl https://syntology.ai/api/ran/2501.08453.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.08453.svg)](https://syntology.ai/paper/2501.08453)

Connect an agent — have() is free.