Tencent Hunyuan releases open-source Hy-Nomas interactive video world model

1. 10:23 PM
   ModelScope@ModelScope2022Official

   Tencent Hunyuan releases Hy-Nomas for interactive video world generation

   AIModelScope 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.

   

1. 1:45 AM
   Tencent · new models on Hugging FaceOfficialPick

   Tencent releases Hy-Nomas, a distilled free-form interactive video world model

   AITencent releases Hy-Nomas-Diffusers, a distilled BF16 version of its Hy-Nomas video world generation model on Hugging Face. The model generates video segment by segment from text instructions and camera control, with a persistent KV cache carrying context between segments. The example uses 4 denoising steps at 704 × 1280 resolution and 24 FPS, and the model is licensed under Apache-2.0.

1. 1:00 PM
   Tencent Hy@TencentHunyuanOfficialPick

   Tencent Hunyuan releases Hy-Nomas, an open-source interactive video world model

   AITencent Hunyuan announces Hy-Nomas, an open-source video world model that accepts free-form interaction through text prompts and camera trajectories. The post says it supports long-horizon generation with world memory, lightweight LoRA adaptation for domains such as robotics, and inference optimized for consumer GPUs. The model is available on the project website, GitHub, and Hugging Face.

   

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.