pith. sign in
Pith Number

pith:KSL44R7P

pith:2025:KSL44R7PRTQF47XVXVL6LVJ3YK
not attested not anchored not stored refs pending

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

Anbang Ye, Binluo Wang, Chaoyu Gong, Chenhui Shen, Gang Ren, Guojun Lei, Hang Xu, Hongxin Liu, Leijun Cheng, Limin Zhang, Minghao Li, Mingyan Jiang, Qianran Ma, Ruijie Zhang, Shijie Huang, Silan Hu, Tom Young, Wanying Liang, Wenjun Li, Xiang Lian, Xiangyu Peng, Xiaokang Wang, Xinying Guo, Xiwen Wu, Yang You, Yuanheng Zhao, Yuhui Wang, Yuqi Wang, Yuting Zhong, Yuxuan Lou, Zangwei Zheng, Zhuangyan Li, Ziang Wei

A commercial-level video generation model can be trained for $200,000.

arxiv:2503.09642 v3 · 2025-03-12 · cs.GR · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KSL44R7PRTQF47XVXVL6LVJ3YK}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. 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.

C2weakest assumption

That the reported $200k training cost accurately captures all resources used and that the human evaluations and VBench scores provide an unbiased, apples-to-apples comparison to the referenced leading models without undisclosed differences in evaluation protocols or model capabilities.

C3one line summary

Open-Sora 2.0 achieves commercial-level video generation quality at a training cost of only $200k through data curation, architecture, training strategy, and system optimizations, and is released fully open-source.

Formal links

2 machine-checked theorem links

Cited by

28 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:47.922770Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

5497ce47ef8ce05e7ef5bd57e5d53bc288aad95588ff80f60b0f1c0d805d8e4d

Aliases

arxiv: 2503.09642 · arxiv_version: 2503.09642v3 · doi: 10.48550/arxiv.2503.09642 · pith_short_12: KSL44R7PRTQF · pith_short_16: KSL44R7PRTQF47XV · pith_short_8: KSL44R7P
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KSL44R7PRTQF47XVXVL6LVJ3YK \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 5497ce47ef8ce05e7ef5bd57e5d53bc288aad95588ff80f60b0f1c0d805d8e4d
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "f7c4092b7e10da5672e51ea7ad0ec03253d5920ee242e24bb989f422645577ae",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.GR",
    "submitted_at": "2025-03-12T05:00:07Z",
    "title_canon_sha256": "7bf382ab4a32a6050bc9e324b5edf8938869a6638ded6c8e33a20c747c0c462c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.09642",
    "kind": "arxiv",
    "version": 3
  }
}