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.
AIWhy it matters.
The model card specifies a distilled BF16 Diffusers release, its four-step denoising setup and camera conditioning, useful for judging how interactive video world models run.
Source details
Tencent · new models on Hugging Face · huggingface.coPublished · added here
Original title: tencent/Hy-Nomas-Diffusers