# Tencent Hunyuan releases Hy-Nomas for interactive video world generation

> Original title: Hy-Nomas has landed. Create an interactive video world and guide its evolution with text and camera control.

- Source: ModelScope
- Published: 2026-10-27T02:23:01.000Z
- Bad Influence: https://badinfluence.news/items/hdxcmm9cd7o7k5qjmlb88rnhd
- Original: https://x.com/ModelScope2022/status/2114905680171745321

## Summary

ModelScope announces Hy-Nomas, a model that generates interactive video worlds from text and camera trajectories. The distilled setting generates each segment in 8 denoising steps at 720 × 1280 and 24 FPS. A low-memory configuration uses quantized weights and CPU offload to run on a single GPU, and the model is released under Apache 2.0.

## Post

Hy-Nomas has landed. Create an interactive video world and guide its evolution with text and camera control.
🤖 https://modelscope.ai/models/Tencent-Hunyuan/Hy-Nomas

⚡ 8-step video generation: The distilled configuration generates each segment in 8 denoising steps, with 720 × 1280 output at 24 FPS.
🖥️ Single-GPU inference: A low-memory configuration uses quantized weights and CPU offload to run video inference on one GPU.
🌍 Shape the world as it unfolds: Use multi-turn prompts to introduce objects, change scenes and styles, or describe new actions.
🎥 Control the camera: Guide viewpoint and movement with camera trajectories alongside text instructions.
🧠 Carry context forward: A KV cache retains context from earlier segments as generation continues.
📊 Evaluate interactive worlds: Hy-Nomas-Bench includes 280 cases covering text interaction, camera navigation, combined control, and spatial memory.
🛠️ Adapt and explore: Supports LoRA fine-tuning and offers a web demo for interactive generation.
📜 Apache 2.0. Third-party components are subject to their own licenses.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2114904966313676800%2Fimg%2FQzcj0I7_CRX1a_sR.jpg&mode=thumb&exp=1793491200&sig=d6281509dceed1ea)