On April 17th, Kunlun Wanwei announced the official launch of TianGong 3.0 Base Model and TianGong SkyMusic Music Grand Model on the occasion of the first anniversary of TianGong’s inception.

Information indicates that TianGong 3.0 boasts 400 billion parameters, surpassing Grok-1’s 314 billion parameters. It exhibits groundbreaking performance improvements in areas such as semantic understanding, logical reasoning, universality, generalization, uncertainty knowledge, and learning ability, with enhancements exceeding 30% in mathematical/reasoning/code/creative writing capabilities.

According to reports, TianGong SkyMusic adopts a self-developed large model music audio generation technology route. This route directly achieves integrated end-to-end music generation of instruments, vocals, melodies, volume, and notes through large model technology. Furthermore, TianGong SkyMusic also possesses original capabilities in reference music generation and dialect song generation.

Specifically, users can upload their own reference music or choose from the existing reference music in the TianGong SkyMusic database to generate songs with similar styles and singing styles, further lowering the barrier to entry for music grand models. In addition, the music generated by TianGong SkyMusic not only excels in areas such as naturalness of vocals and understandability of lyrics but also supports numerous dialects such as Cantonese, Chengdu dialect, and Beijing dialect, allowing users to express themselves more freely through music.