Skip to content
Agientry
← Back to Videos

Hy-Nomas: An Open-Source Free-Form Interactive Video World Model

Loading video
Loading video

Tencent Hunyuan open-sources Hy-Nomas: free-form interaction via text and camera trajectories, world memory for long-horizon generation, lightweight LoRA adaptation for domains such as robotics, and consumer-GPU inference.

World ModelsVideo GenerationTencent HunyuanLoRA
Category: research
Author: @TencentHunyuan
Date: 2026-10-23T00:00:00
Duration: 141.417s
Source: https://x.com/TencentHunyuan/status/2113676827114053892
Reference: https://github.com/Tencent-Hunyuan/Hy-Nomas

Related Videos

WorldCrafter: Video World Exploration Without 3D Reconstruction
2:53

WorldCrafter: Video World Exploration Without 3D Reconstruction

@TencentAI_News · 780 views · 2026-09-23
World ModelsVideo Generation
GWM Worlds 2 Makes Video and Audio Into Real-Time Simulation
0:12

GWM Worlds 2 Makes Video and Audio Into Real-Time Simulation

@c_valenzuelab · 851 views · 2026-09-03
GWM Worlds 2Runway
SolarWM Turns Minimax H3 Into Realtime Interactive Worlds
0:48

SolarWM Turns Minimax H3 Into Realtime Interactive Worlds

@aisearchio · 1.1k views · 2026-09-04
SolarWMWorld Models
GAE: A Geometry-Native Latent Space for 3D-Consistent World Generation
0:51

GAE: A Geometry-Native Latent Space for 3D-Consistent World Generation

@HuggingPapers · 794 views · 2026-09-23
World Models3D Generation
HarnessEval-W: an agentic benchmark for visual world models
1:17

HarnessEval-W: an agentic benchmark for visual world models

@MirroS_ai · 727 views · 2026-08-18
World ModelsBenchmarks
Veda Sparse Attention Speeds Up Video Character Replacement in ComfyUI
0:27

Veda Sparse Attention Speeds Up Video Character Replacement in ComfyUI

@ai_hakase_ · 214 views · 2026-10-13
Video GenerationSparse Attention

As an Amazon Associate, we earn from qualifying purchases.