<ul><li>A new open-weights AI video synthesis model, Tencent's HunyuanVideo, is capable and openly distributed.</li><li>The model can be run locally under the right circumstances and can be fine-tuned or used with LoRAs to teach it new concepts.</li><li>Chinese companies have been leading in AI video, possibly due to their less reticence to train on copyrighted materials and incorporate uncensored video sources.</li><li>HunyuanVideo allows uncensored outputs and can generate videos of anatomically realistic, nude humans.</li></ul>

A new, uncensored AI video model may spark a new AI hobbyist movement

Discover more