# Tencent Releases Hy-Nomas, an Interactive Video World Model

> The open-weights model pairs text- and image-to-video generation with action-aware causal attention and explicit camera control.

Published by The Open Weights on Oct 21, 2026. Canonical: https://theopenweights.com/news/hy-nomas-euxj

## Key facts

- Company: Tencent
- Model: Hy-Nomas
- Version: Hy-Nomas
- Category: Text → Video
- Modalities: Image → Video, Text → Video
- License: Other (Open weights, commercial use allowed)
- Significance: notable
- Published: 2026-10-21
- Last verified: 2026-10-28
- Hugging Face: https://huggingface.co/tencent/Hy-Nomas
- Canonical URL: https://theopenweights.com/news/hy-nomas-euxj

Tencent has released [Hy-Nomas](https://huggingface.co/tencent/Hy-Nomas), an interactive video world model that generates video from both text and image prompts. Unlike standard clip generators, Hy-Nomas is designed to respond to actions and camera movement as it unfolds a scene, positioning it closer to the emerging class of "world models" than to one-shot video synthesis tools.

The model's defining feature is action-aware causal attention, a design that lets each generated frame depend on prior frames and on user-supplied inputs in a time-ordered way. Paired with explicit camera control, that approach is meant to produce footage you can steer — adjusting viewpoint and prompting behavior — rather than simply rendering a fixed sequence end to end.

## Why it matters

Interactive and controllable video generation is quickly becoming the next frontier beyond text-to-video, with applications in simulation, game-like environments, and embodied AI research. Open releases in this space remain comparatively rare, so a model from a major lab that ships weights publicly gives researchers and developers something concrete to build on.

A few things to keep in mind:

- Hy-Nomas supports both text-to-video and image-to-video workflows.
- It is distributed under a custom ("other") license, so teams should review the terms before commercial use.
- Tencent has not published parameter counts, resolution, or duration specs in the release record.

As an initial release, Hy-Nomas establishes a baseline for Tencent's interactive video work. The full model card and any usage details are available on [Hugging Face](https://huggingface.co/tencent/Hy-Nomas).

## Get the model

- [Hugging Face](https://huggingface.co/tencent/Hy-Nomas)

## Sources

- [tencent/Hy-Nomas](https://huggingface.co/tencent/Hy-Nomas) — Hugging Face, Oct 21, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent Releases Hy-Nomas, an Interactive Video World Model", The Open Weights, Oct 21, 2026, https://theopenweights.com/news/hy-nomas-euxj