SenseTime reportedly open-sources SenseNova 6.8 Code2Video, a 27B code-to-video model

A Chinese AI blogger reports that SenseTime open-sourced SenseNova 6.8 Code2Video on October 27, with weights on Hugging Face under sensenova/SenseNova-6.8-Code2Video. The report is second-hand; SenseTime's own announcement is not cited.

According to the blogger, the model has 27B parameters and makes video by first writing code for the visual effects rather than generating pixels directly. That makes later edits more like engineering work, and the blogger suggests it suits explainer videos that need precise control over detail. The post shows two examples: a retro airport flip-board and a video built from a product demo clip.