Tencent Hunyuan interactive world model generating real-time, controllable 720p video with memory for consistency.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Hy-Nomas is an interactive world model from Tencent's Hunyuan team. According to its project page, it covers multi-turn direction, camera control and long-form 720p video generation, and the site shows recorded model outputs alongside research material.
A creator review describes it as a real-time system that generates short video segments in sequence, using a memory mechanism to keep scenes consistent across segments. Output is reported as 720p at 24 fps. The same review states that code, training scripts and models are released under Apache 2.0; this was not confirmed on the fetched pages, and no GitHub or Hugging Face links were found.
Access details, hardware requirements and pricing were not available in the provided material. It appears to be a research release aimed at developers and researchers working on world models and interactive video generation.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time interactive world model that generates short segments with memory for consistency. Outputs 720p at 24 fps. Code, training scripts and models are released under Apache 2.
Closest neighbours by meaning, not just by category.
Research · Tencent
Tencent Hunyuan research framework that turns one text prompt into an explorable, editable open-world 3D scene.
Model
Interactive autoregressive world model generating minute-long playable video with real-time camera control and prompt events.
Model · Tencent
Tencent's unified multimodal model for 3D understanding, text-to-3D generation, instruction-based editing and part generation.
Model
Research multi-player video world model with hierarchical communication, trained on 4 players and run with up to 10.
Model
Real-time interactive world model with compressed memory and hybrid action and semantic control, built on Wan 2.2.
Model · NVIDIA
NVIDIA's 2.8B-parameter world model for minute-long, camera-controlled 720p video generation on a single GPU.
