AI News Live

SenseTime Unveils 8B Multimodal Model with 4K Image Output

SenseTime has open-sourced an 8 billion parameter multimodal model capable of generating native 4K image outputs, pushing the boundaries of AI-generated media.

The model integrates multiple modalities, including images, audio, and video.

4K image output capability represents a significant advancement in AI-generated visual content.

Open-sourcing the model aims to foster innovation and broader adoption.

Source: https://news.google.com/rss/articles/CBMipgFBVV95cUxONHRlWHhQQkJjRUVjRzNqZjZlQzMxd1RjbmdBY0RQSXg2amdqbnd6OEVnbkxDeE8xdVdKaWt6cEp5SXQwYzZHamxmZ3hpWkxfZDRlNUkwVy1TR0V3MU1SZmdIcnRaNnZfc2JjdWRNXzJhN2xNSm9SREpaT3BvM2xJRXM5UUJSTTVrYnBaVWJkZXJhMTI4NnJzUm1hZjNOdzk3WDlmb3l3?ucbcb=1&hl=en-US&gl=US&ceid=US:en