HunyuanVideo 1.5

What it is

HunyuanVideo 1.5 is Tencent’s open-weights video model, released on 20 November 2025, and its significance is as much about who is publishing it as what it does. A correction, first, to what this page previously said: the model is not Apache 2.0. The licence file in Tencent’s own repository is the Tencent Hunyuan Community License Agreement, which names the European Union, the United Kingdom and South Korea as excluded territories and requires a separate licence above 100 million monthly active users. That a company the size of Tencent publishes a capable video model’s weights at all is still the headline; the terms they come on need reading much more carefully than a permissive licence would.

Open weights versus open source

Open weights and open source are worth separating. Many models described as open are, in practice, free to download but bound by licences that restrict who may use them, where and at what scale, and HunyuanVideo 1.5 sits in exactly this category. Apache 2.0, the licence this page once wrongly attributed to it, lets a business anywhere use, adapt and ship a model commercially with no territorial carve-outs. The Hunyuan community licence does not: a team in London or Paris is outside its named territories altogether, whatever its size. For a UK business deciding what to build on, the difference is the one between a model it can depend on and a model it is not licensed to run at all.

Against the clean options

The comparison with LTX-2.3 and Wan 2.7 places it precisely. Those two carry genuinely permissive terms, with LTX-2.3 under Apache 2.0 up to a revenue threshold, and either can sit in a UK production stack without a territorial question. HunyuanVideo 1.5 offers comparable capability but not comparable freedom, and the same pattern has since repeated at the top of the leaderboard: MiniMax H3’s community licence also excludes the UK, EU, US and South Korea. The open end of the video market now splits less by weight availability than by where the licence lets you stand.

Breadth across media

What sets Tencent apart is breadth. HunyuanVideo 1.5 is one product in the wider Hunyuan family, which covers text, image, video, 3D and world models. Very few organisations publish open weights across all of those categories at once, and doing so makes Tencent arguably the most complete open-weights publisher of any large company anywhere. The strategic logic is that a lab which can generate text, pictures, moving footage, three-dimensional assets and interactive world models from a single family is building an entire open toolkit rather than a single open product, and each piece reinforces the others. A studio that adopts one Hunyuan model has an obvious reason to try the next.

That completeness is the thing to watch. Owning an open stack that spans several media is a different proposition from shipping one strong model, because it lets Tencent set a baseline of free capability across the whole creative pipeline rather than in a single corner of it. For the open video market specifically, the model deepens the pool of published weights without widening the pool a UK business can lawfully adopt, and a reader here should weigh it accordingly. For a business, the appeal of adopting from a single family is practical: shared tooling, consistent licensing and one relationship to understand rather than a patchwork of vendors, each with its own terms.

Where it sits

Where this leaves the wider AI video field is a market splitting in two. At one end sit the paid, closed APIs that compete on peak quality and integration; at the other, a growing set of open-weight models that compete on price and freedom, with the freedom on offer varying licence by licence and territory by territory. HunyuanVideo 1.5 is a marker of how far the open side has come, and of how willing the largest technology companies now are to compete by giving capability away. For the broader picture of what these labs are releasing, the AI hub tracks the same pattern across text and images.