NodeValid

Published video-model weights, licences and hardware notes

HunyuanVideo: what the repository publishes

HunyuanVideo publishes weights for a model of over 13 billion parameters under a licence the vendor wrote itself rather than a standard permissive one. The repository states 60GB of peak GPU memory at its larger setting, measured on a single 80G card. As of 2026-09-12.

What the repositories actually stateFilled where the repository states something, hollow where it does not. A blank is not an inference.What the repositories actually stateWhat is statedLicenceLicence — What is stated: tencent-hunyuan-communitySizeSize — What is stated: Over 13 billion parametersHardwareHardware — What is stated: 60GB peak at 720px1280px, 129 framesResolutionResolution — What is stated: No output size recordedLengthLength — What is stated: 129 frames, as a measurement setting
Fig. 1 Filled where the repository states something, hollow where it does not. A blank is not an inference.
The five fields this register keeps, for HunyuanVideo. Read from the vendor's own repository and Hugging Face model card on 2026-09-12.
FieldWhat is statedDetail
Licencetencent-hunyuan-communityA vendor-written licence, not a standard permissive one
SizeOver 13 billion parametersStated in the repository
Hardware60GB peak at 720px1280px, 129 frames45GB at 544px960px, on a single 80G GPU
ResolutionNo output size recordedIts pixel dimensions size the memory figures instead
Length129 frames, as a measurement settingFrames, sizing a memory figure rather than a ceiling

Inclusion rule. The same five fields for every family here. A field the repository does not state is recorded as not stated rather than estimated from the parameter count. Order. Fixed field order, identical on every family page.

1A vendor-written licence is a different thing from Apache 2.0

Nine of the 15 families in this register carry a licence whose text is standard and whose terms a reader has cleared once and for all. This one carries a licence named after the company that wrote it, which means the terms have to be read rather than assumed.

This register records the licence name and does not summarise its terms. A one-line paraphrase of a bespoke licence is exactly the kind of helpfulness that turns into somebody relying on a wrong reading, and the licence file is one click from the row.

The HunyuanVideo model card as it appeared on 16 September 2026.
Fig. 2 A model card rather than a code repository, which is where this family states its memory figures.Screenshot of huggingface.co/tencent/HunyuanVideo, captured 2026-09-16. Reproduced to show where this entry was read from.

2The memory figures are stated per setting, which is unusually clear

Sixty gigabytes at the larger resolution and frame count, forty-five at the smaller. Most repositories publish one number or none; publishing two with the settings attached lets a reader work out which side of a hardware boundary their intended output falls on.

Both figures sit well above anything a desktop card offers, so this family is a rented-server proposition rather than a local one on the published evidence.

3What the register does not carry for this family

No hosted service in this register names this model on a priced page, so there is no seconds rate to set against the hardware. That leaves the cost comparison open in one direction: the hardware cost is knowable and the alternative is not.

The row will appear if a service starts naming it. Until then the family sits in this register as published weights with no commercial counterpart to compare against.

4The same field, across every family

Licence, family by familyOne field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.Licence, family by familyLicenceAllegro — Licence: apache-2.0AllegroCogVideoX — Licence: Split by model sizeCogVideoXCosmos Predict 2.5 — Licence: NVIDIA Open Model LicenseCosmos Predict 2.5FramePack — Licence: Apache 2.0FramePackHunyuanVideo — Licence: tencent-hunyuan-communityHunyuanVideoLongCat-Video — Licence: MIT LicenseLongCat-VideoLTX-Video — Licence: Apache 2.0LTX-VideoMAGI-1 — Licence: Apache License 2.0MAGI-1Mochi 1 — Licence: Apache 2.0Mochi 1Open-Sora — Licence: Apache 2.0Open-SoraPyramid Flow — Licence: stabilityai-ai-communityPyramid FlowSkyReels-V2 — Licence: skywork-licenseSkyReels-V2Stable Video Diffusion — Licence: stable-video-diffusion-communityStable Video DiffusionStep-Video-T2V — Licence: MITStep-Video-T2VWan — Licence: Apache 2.0Wan
Fig. 3 One field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.
Every family on one field, with HunyuanVideo marked. Recorded 2026-09-22.
FamilyLicence
Allegroapache-2.0
CogVideoXSplit by model size
Cosmos Predict 2.5NVIDIA Open Model License
FramePackApache 2.0
HunyuanVideotencent-hunyuan-community
LongCat-VideoMIT License
LTX-VideoApache 2.0
MAGI-1Apache License 2.0
Mochi 1Apache 2.0
Open-SoraApache 2.0
Pyramid Flowstabilityai-ai-community
SkyReels-V2skywork-license
Stable Video Diffusionstable-video-diffusion-community
Step-Video-T2VMIT
WanApache 2.0

Inclusion rule. Families whose vendor has published weights openly. A family whose repository does not state this particular field keeps its row, marked hollow. Order. Alphabetical by family name.

Size, family by familyOne field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.Size, family by familySizeAllegro — Size: VAE 175M and DiT 2.8BAllegroCogVideoX — Size: 2B and 5B, carried in the model namesCogVideoXCosmos Predict 2.5 — Size: 2,059,174,912 parametersCosmos Predict 2.5FramePack — Size: 13B modelsFramePackHunyuanVideo — Size: Over 13 billion parametersHunyuanVideoLongCat-Video — Size: 13.6B parametersLongCat-VideoLTX-Video — Size: A 13B modelLTX-VideoMAGI-1 — Size: 24B and 4.5B modelsMAGI-1Mochi 1 — Size: 10 billion parametersMochi 1Open-Sora — Size: An 11B modelOpen-SoraPyramid Flow — Size: No parameter count recordedPyramid FlowSkyReels-V2 — Size: 1.3B, 5B and 14B variantsSkyReels-V2Stable Video Diffusion — Size: 2B paramsStable Video DiffusionStep-Video-T2V — Size: 30 billion parametersStep-Video-T2VWan — Size: A 5B text-to-video and image-to-video modelWan
Fig. 4 One field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.
Every family on one field, with HunyuanVideo marked. Recorded 2026-09-22.
FamilySize
AllegroVAE 175M and DiT 2.8B
CogVideoX2B and 5B, carried in the model names
Cosmos Predict 2.52,059,174,912 parameters
FramePack13B models
HunyuanVideoOver 13 billion parameters
LongCat-Video13.6B parameters
LTX-VideoA 13B model
MAGI-124B and 4.5B models
Mochi 110 billion parameters
Open-SoraAn 11B model
Pyramid FlowNo parameter count recorded
SkyReels-V21.3B, 5B and 14B variants
Stable Video Diffusion2B params
Step-Video-T2V30 billion parameters
WanA 5B text-to-video and image-to-video model

Inclusion rule. Families whose vendor has published weights openly. A family whose repository does not state this particular field keeps its row, marked hollow. Order. Alphabetical by family name.

Hardware, family by familyOne field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.Hardware, family by familyHardwareAllegro — Hardware: 9.3G BF16 with cpu_offloadAllegroCogVideoX — Hardware: From 4GB in FP16 on the 2BCogVideoXCosmos Predict 2.5 — Hardware: 32.54 GB of GPU VRAMCosmos Predict 2.5FramePack — Hardware: 6GB minimum for 1800 frames at 30fpsFramePackHunyuanVideo — Hardware: 60GB peak at 720px1280px, 129 framesHunyuanVideoLongCat-Video — Hardware: No memory figure recordedLongCat-VideoLTX-Video — Hardware: No minimum statedLTX-VideoMAGI-1 — Hardware: H100 or H800 x 8 for the 24BMAGI-1Mochi 1 — Hardware: About 60GB VRAM on a single GPUMochi 1Open-Sora — Hardware: 60.3GB peak at 768px on one GPUOpen-SoraPyramid Flow — Hardware: No memory figure recordedPyramid FlowSkyReels-V2 — Hardware: About 14.7GB peak on the 1.3B at 540PSkyReels-V2Stable Video Diffusion — Hardware: About 180s on an A100 80GB cardStable Video DiffusionStep-Video-T2V — Hardware: 78.55 GB peak at 768px768px204fStep-Video-T2VWan — Hardware: A consumer 4090 on the 5B releaseWan
Fig. 5 One field at a time, every family beside it, HunyuanVideo marked. Quoted from each repository and never derived from a parameter count. The exact phrasing sits in the table under this figure. Recorded 2026-09-22.
Every family on one field, with HunyuanVideo marked. Recorded 2026-09-22.
FamilyHardware
Allegro9.3G BF16 with cpu_offload
CogVideoXFrom 4GB in FP16 on the 2B
Cosmos Predict 2.532.54 GB of GPU VRAM
FramePack6GB minimum for 1800 frames at 30fps
HunyuanVideo60GB peak at 720px1280px, 129 frames
LongCat-VideoNo memory figure recorded
LTX-VideoNo minimum stated
MAGI-1H100 or H800 x 8 for the 24B
Mochi 1About 60GB VRAM on a single GPU
Open-Sora60.3GB peak at 768px on one GPU
Pyramid FlowNo memory figure recorded
SkyReels-V2About 14.7GB peak on the 1.3B at 540P
Stable Video DiffusionAbout 180s on an A100 80GB card
Step-Video-T2V78.55 GB peak at 768px768px204f
WanA consumer 4090 on the 5B release

Inclusion rule. Families whose vendor has published weights openly. A family whose repository does not state this particular field keeps its row, marked hollow. Order. Alphabetical by family name.

5Open weights, hosted

Instead of local hardware for “HunyuanVideo”, SceneMixer runs hosted models; its guides describe the result:

Typically 60–120 seconds, always 9:16 vertical, ending on a hook. SceneMixer's episode outlines are generated with that pacing, and setting a project to 9:16 makes every segment vertical (the default is 16:9).

SceneMixer, How to Make ReelShort-Style Dramas with AI — “How long is a ReelShort-style episode?” (read 2026-10-13)

Doubao Seed 2.1 Pro is the family’s full-size tier at 100% of the base text rate, twice the default. Same three jobs — reading, writing, storyboards — with more headroom on long, crowded episodes: it holds the storyboard’s strict format more reliably and keeps track of many characters and locations in one pass.

SceneMixer, Doubao Seed 2.1 Pro (read 2026-10-13)

6Sources

Read from github.com/Tencent-Hunyuan on 2026-09-12. Hardware figures across every family are collected on requirements; the licence column is set out on licence and what counts as a published weight is on the method page. Previous family: LongCat-Video. Next family: CogVideoX.