# Tencent releases Hy‑Nomas text‑to‑video model on Hugging Face

> Hy‑Nomas lets users build a video world segment by segment with text prompts and camera control, available for demo and download Oct 21 2026.

Oossa · 2026-10-23 · https://oossa.com/en/tencent-releases-hy-nomas-text-to-video-model-on-hugging-face

Tencent Hunyuan has added a new model called Hy‑Nomas to Hugging Face. It generates video worlds one segment at a time, letting users add objects, change style, or move the camera through multi‑turn text instructions. A distilled version runs in eight denoising steps at 720 × 1280 resolution, 24 FPS, and a single‑GPU setup works on an RTX 4090 with INT8 weights. The model and a benchmark suite, Hy‑Nomas‑Bench, are available for download along with a web demo.

## The facts

- Model published on Hugging Face on 2026‑10‑21
- Distilled inference uses 8 denoising steps, outputs 720 × 1280 video at 24 FPS

## Why it matters

Creators can experiment with interactive video generation on a single high‑end GPU without needing large cloud clusters.

## Sources & references

1. [New model on Hugging Face: tencent/Hy-Nomas (text-to-video)](https://huggingface.co/tencent/Hy-Nomas) – Tencent Hunyuan, 2026-10-21
2. [New repository Tencent-Hunyuan/Hy-Nomas](https://github.com/Tencent-Hunyuan/Hy-Nomas) – Tencent Hunyuan, 2026-10-21
3. [New model on Hugging Face: tencent/Hy-Nomas-Diffusers](https://huggingface.co/tencent/Hy-Nomas-Diffusers) – Tencent Hunyuan, 2026-10-24

Last updated: 2026-10-24