Model · Tencent · Open weights

HunyuanVideo-1.5

Text-to-videoImage-to-videoOpen weights
Open the AIContentDrop generator →
Arena rating
No votes yet
Votes
No votes yet
Arena status
Pre-launch
Facts checked
2026-10-06

Vendor-sourced facts

Published facts for HunyuanVideo-1.5 — vendor-sourced, checked 2026-10-06
FactValue
VendorTencent [1]
LicenceOpen weights (tencent-hunyuan-community license; weights downloadable at huggingface.co/tencent/HunyuanVideo-1.5, code at github.com/Tencent-Hunyuan/HunyuanVideo-1.5) [1]
ModesText-to-video, Image-to-video [1]
Release2025-11-20 [1]
Max resolution1080p [1]
Max clip duration10 s [1]
Native audioNo [1]
Accessopen weights [1]
Vendor pagehttps://huggingface.co/tencent/HunyuanVideo-1.5 [1]

Arena rating: no votes yet. Nothing on this page is a score, a rank or a measurement by us — every value is what Tencent publishes, with the page it came from listed under Sources.

Crowd votes · external board

Not listed on the Design Arena video board (checked 2026-10-21).[2]

About HunyuanVideo-1.5

HunyuanVideo-1.5 is Tencent's open-weights model from November 2025, downloadable from Hugging Face with the code on GitHub under the tencent-hunyuan-community licence. [1] Unlike every other entry it is listed with open weights as its only access route in our catalogue: there is no first-party hosted app in the source we checked.

It is also the only model here that explicitly does not generate audio, and Tencent's own description emphasises 8.3 billion parameters as the point of the release. [1] A silent 1080p ten-second model that runs on your own hardware is a different tool from a 4K audio model behind an API, and the arena will not pretend those are the same purchase.

“A lightweight yet powerful video generation model that achieves state-of-the-art visual quality with only 8.3 billion parameters”

Tencent on HunyuanVideo-1.5 [1]

Want hands-on context before trusting anyone's ranking? Generate your own clips with a multi-model workflow on AIContentDrop: try a hosted multi-model workflow · hook your toolchain up with MCP.

Sources

  1. Tencent — HunyuanVideo-1.5, vendor documentation https://huggingface.co/tencent/HunyuanVideo-1.5 — checked 2026-10-06
  2. Design Arena — video leaderboard https://www.designarena.ai/leaderboard/video — checked 2026-10-21

Each [n] above is the vendor page the fact beside the marker was read from, on the date shown. Where a vendor states nothing, the table says “Not stated” and no value is inferred from anywhere else.