SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.09642 · 2025

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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 6 have no contract verdict; 1 failure of our instrument; 4 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/2503.09642.json · badge: /api/ran/2503.09642.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
hpcaitech/open-sora canonical (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
FunctionStatusWhere it lives
apply Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/sampler.py
pointer only (licence: Apache-2.0) · get_code("6ddc087f93460147")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

collate_fn_default Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/dataloader.py
pointer only (licence: Apache-2.0) · get_code("b1397d87ab4baaa0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

gather_forward_split_backward Ran
ran; our contract draft was wrong, not the code
hpcaitech/open-sora/opensora/acceleration/communications.py
pointer only (licence: Apache-2.0) · get_code("97c082db7efd0240")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_aspect_ratios_dict Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/aspect.py
pointer only (licence: Apache-2.0) · get_code("ac4e5200cca6d741")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_num_pexels Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/aspect.py
pointer only (licence: Apache-2.0) · get_code("68f3ad1e8b47c4ea")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_ratio Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/aspect.py
pointer only (licence: Apache-2.0) · get_code("898176aac6eec0f7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_seed_worker Ran
ran on a synthesized input
hpcaitech/open-sora/opensora/datasets/dataloader.py
pointer only (licence: Apache-2.0) · get_code("e4a4611bb6f33d1b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

all_to_all Not yet run
unverified (harvested, no recorded run)
hpcaitech/open-sora/opensora/acceleration/communications.py
pointer only (licence: Apache-2.0) · get_code("b51f59051d16f7df")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

get_data_parallel_group Not yet run
unverified (harvested, no recorded run)
hpcaitech/open-sora/opensora/acceleration/parallel_states.py
pointer only (licence: Apache-2.0) · get_code("ae3b5ad7195807b2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

read_video_cv2 Not yet run
unverified (harvested, no recorded run)
hpcaitech/open-sora/opensora/datasets/read_video.py
pointer only (licence: Apache-2.0) · get_code("14e5749dbd18dd9b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

split_forward_gather_backward Not yet run
unverified (harvested, no recorded run)
hpcaitech/open-sora/opensora/acceleration/communications.py
pointer only (licence: Apache-2.0) · get_code("a771d32bab25e50b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hpcaitech/open-sora, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
all_to_all 1 other paper
1 dated earlier
2411.16375 (2024-11)
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
gather_forward_split_backward 1 other paper
1 dated earlier
2411.16375 (2024-11)
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
split_forward_gather_backward 1 other paper
1 dated earlier
2411.16375 (2024-11)
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

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

Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only $200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.

For agents

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

get_harvested_code_for_paper("2503.09642")
get_code_for_paper("2503.09642")
have("2503.09642")

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

curl https://syntology.ai/api/ran/2503.09642.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.09642.svg)](https://syntology.ai/paper/2503.09642)

Connect an agent — have() is free.