Papers › HunyuanVideo: A Systematic Framework For Large Video Generative Models

HunyuanVideo: A Systematic Framework For Large Video Generative Models

3 Dec 2024arXiv:2412.03603archive 2025-07-28

Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, Kathrina Wu, Qin Lin, Junkun Yuan, Yanxin Long, Aladdin Wang, Andong Wang, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Hongmei Wang, Jacob Song, Jiawang Bai, Jianbing Wu, Jinbao Xue, Joey Wang, Kai Wang, Mengyang Liu, Pengyu Li, Shuai Li, Weiyan Wang, Wenqing Yu, Xinchi Deng, Yang Li, Yi Chen, Yutao Cui, Yuanbo Peng, Zhentao Yu, Zhiyu He, Zhiyong Xu, Zixiang Zhou, Zunnan Xu, Yangyu Tao, Qinglin Lu, Songtao Liu, Dax Zhou, Hongfa Wang, Yong Yang, Di Wang, Yuhong Liu, Jie Jiang, Caesar Zhong

Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at https://github.com/Tencent/HunyuanVideo.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 27 code samples: 26 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 27: 18 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 16 ran (6 with no instrument failure; 10 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 18 samples that ran has no recorded date.

tencent/hunyuanvideo officialmentioned in papermentioned on GitHubpytorchSyntology: 25 samples, 16 ran (10 instrument-failed) · 9 unverified report
tencent-hunyuan/hunyuanvideo mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

27 samples harvested: 18 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran · our draft was wrong
2ran; the contract check could not run
6ran
9unverified

Licence: 27 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

tencent/hunyuanvideo official repository 25 samples, 16 ran (10 instrument-failed) · 9 unverified
FinalLayer in 29 papers hyvideo/modules/models.py ran licence not identified · pointer only · db1fce6ba128923c · report fixture: returned FinalLayer · level recorded 2026-09-22
MLPEmbedder hyvideo/modules/models.py ran licence not identified · pointer only · fcbb385d2327fafe · report fixture: returned MLPEmbedder · level recorded 2026-09-22
ModulateDiT hyvideo/modules/models.py ran licence not identified · pointer only · 8f5178a632e5b33b · report fixture: returned ModulateDiT · level recorded 2026-09-22
RMSNorm in 61 papers hyvideo/modules/models.py ran licence not identified · pointer only · 9fa452fc273f7d2a · report fixture: returned RMSNorm · level recorded 2026-09-22
TextProjection hyvideo/modules/models.py ran fingerprinted licence not identified · pointer only · 5f07c9ec80c3ada3 · report fixture: returned TextProjection · level recorded 2026-09-22
TimestepEmbedder in 27 papers
census: 9 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
hyvideo/modules/models.py ran licence not identified · pointer only · 972e92f9877ffd4e · report fixture: returned TimestepEmbedder · level recorded 2026-09-22
apply_gate hyvideo/modules/models.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 51349c7b63b0eefe · report fixture: signature x:Tensor/2/float, gate:Tensor/1/float, tanh:bool/0/bool · returned Tensor · level recorded 2026-09-22
apply_rotary_emb in 121 papers hyvideo/modules/models.py ran · our draft was wrong licence not identified · pointer only · 11e474d70dbef16a · report fixture: signature xq:Tensor/4/float, xk:Tensor/4/float, freqs_cis:tuple/1/Tensor, head_first:bool/0/bool · returned tuple · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 5 of 5, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32 · arg 3: rank 4, kind float, dtype float32
hyvideo/modules/models.py ran · our draft was wrong licence not identified · pointer only · 7f6ea85164888083 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float, mode:str/0/str, drop_rate:float/0/float, attn_mask:NoneType/0/?, causal:bool/0/bool, cu_seqlens_q:NoneType/0/?, cu_seqlens_kv:NoneType/0/?, max_seqlen_q:NoneType/0/?, max_seqlen_kv:NoneType/0/?, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22
get_activation_layer in 9 papers hyvideo/modules/models.py ran · our draft was wrong licence not identified · pointer only · 3522a7226855625c · report fixture: signature act_type:str/0/str · returned function · level recorded 2026-09-22
get_cu_seqlens hyvideo/modules/models.py ran · our draft was wrong licence not identified · pointer only · 0e540842c62d05e8 · report fixture: returned Tensor · level recorded 2026-09-22
get_norm_layer in 111 papers hyvideo/modules/models.py ran · our draft was wrong licence not identified · pointer only · 73399259c03e64cf · report fixture: signature norm_layer:str/0/str · returned type · level recorded 2026-09-22
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input
hyvideo/modules/models.py ran · our draft was wrong fingerprinted licence not identified · pointer only · b511dab275230850 · report fixture: signature x:Tensor/2/float, shift:Tensor/1/float, scale:Tensor/1/float · returned Tensor · level recorded 2026-09-22
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input
hyvideo/modules/models.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · ca3d87e7de8abdfd · report fixture: signature freqs_cis:Tensor/2/float, x:Tensor/4/float, head_first:bool/0/bool · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 3, kind float, dtype float32
hyvideo/modules/models.py ran · our draft was wrong fingerprinted licence not identified · pointer only · dda8bc930ad44165 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
hyvideo/modules/models.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 1919bf556aed915f · report fixture: signature t:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22
HYVideoDiffusionTransformer hyvideo/modules/models.py unverified licence not identified · pointer only · a45df7821e4bd637 · report
IndividualTokenRefiner hyvideo/modules/models.py unverified licence not identified · pointer only · 6970107014bafe0d · report
IndividualTokenRefinerBlock hyvideo/modules/models.py unverified licence not identified · pointer only · 70c990db928810cb · report
MLP in 375 papers hyvideo/modules/models.py unverified licence not identified · pointer only · 1d7a9726d35da730 · report
MMDoubleStreamBlock hyvideo/modules/models.py unverified licence not identified · pointer only · 58e50396f807550d · report
MMSingleStreamBlock hyvideo/modules/models.py unverified licence not identified · pointer only · cfdd75d23de61f07 · report
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
hyvideo/modules/models.py unverified licence not identified · pointer only · 66ff7f71531c44aa · report
SingleTokenRefiner hyvideo/modules/models.py unverified licence not identified · pointer only · a7d82a605d5baa39 · report
parallel_attention hyvideo/modules/models.py unverified licence not identified · pointer only · ffe9b91817aee3fa · report
tencent-hunyuan/hunyuanvideo community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
retrieve_timesteps in 70 papers hyvideo/diffusion/pipelines/pipeline_hunyuan_video.py ran · our draft was wrong licence not identified · pointer only · f3a81898d239b163 · report fixture: signature scheduler:MockScheduler/0/?, num_inference_steps:int/0/int, device:NoneType/0/?, timesteps:NoneType/0/?, sigmas:NoneType/0/? · returned tuple · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
rescale_noise_cfg in 63 papers
census: 2 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · bea2d776a332f2b0 · report fixture: signature noise_cfg:Tensor/4/float, noise_pred_text:Tensor/4/float, guidance_rescale:float/0/float · returned Tensor · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for HunyuanVideo (graph method: HunyuanVideo). 25 bricks; individually on a fixture: 16 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. HYVideoDiffusionTransformer entry · level 0 · unverified · a45df7821e4bd637
  2. FinalLayer helper · level 1 · ran · db1fce6ba128923c
  3. MLPEmbedder helper · level 1 · ran · fcbb385d2327fafe
  4. MMDoubleStreamBlock model · level 0 · unverified · 58e50396f807550d
  5. MMSingleStreamBlock model · level 0 · unverified · cfdd75d23de61f07
  6. PatchEmbed helper · level 0 · unverified · 66ff7f71531c44aa
  7. SingleTokenRefiner helper · level 0 · unverified · a7d82a605d5baa39
  8. TextProjection helper · level 1 · ran · 5f07c9ec80c3ada3
  9. TimestepEmbedder helper · level 1 · ran · 972e92f9877ffd4e
  10. get_activation_layer helper · level 1 · ran · our draft was wrong · 3522a7226855625c
  11. get_cu_seqlens helper · level 1 · ran · our draft was wrong · 0e540842c62d05e8
  12. modulate helper · level 1 · ran · our draft was wrong · b511dab275230850
  13. MLP helper · level 0 · unverified · 1d7a9726d35da730
  14. ModulateDiT helper · level 1 · ran · 8f5178a632e5b33b
  15. apply_gate helper · level 1 · ran; the contract check could not run (RAISES) · 51349c7b63b0eefe
  16. apply_rotary_emb helper · level 1 · ran · our draft was wrong · 11e474d70dbef16a
  17. attention helper · level 1 · ran · our draft was wrong · 7f6ea85164888083
  18. get_norm_layer helper · level 1 · ran · our draft was wrong · 73399259c03e64cf
  19. parallel_attention helper · level 0 · unverified · ffe9b91817aee3fa
  20. IndividualTokenRefiner helper · level 0 · unverified · 6970107014bafe0d
  21. timestep_embedding helper · level 1 · ran · our draft was wrong · 1919bf556aed915f
  22. reshape_for_broadcast helper · level 1 · ran; the contract check could not run (RAISES) · ca3d87e7de8abdfd
  23. rotate_half helper · level 1 · ran · our draft was wrong · dda8bc930ad44165
  24. RMSNorm helper · level 1 · ran · 9fa452fc273f7d2a
  25. IndividualTokenRefinerBlock helper · level 0 · unverified · 70c990db928810cb

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2412.03603") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Video AlignmentVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections