Zhu Jun, vice president of Tsinghua University's Institute of Artificial Intelligence and founder and chief scientist of Sangji Technology, released Vidu Q1, the industry's first highly controllable AI video big model, on March 29th. 1AI learned from the official, Vidu Q1 in multi-subject detail control (especially action, layout control), sound synchronization control, picture quality enhancement and other aspects have achieved significant results. Taking multi-subject detail controllable as an example, on the basis of semantic commands, by incorporating visual commands of reference diagrams, Vidu Q1 supports the position, size, and...

Recently, Shengshu Technology's "Multimodal Big Model" was officially registered with the national "Interim Measures for the Management of Generative Artificial Intelligence Services". Founded in March 2023, Shengshu Technology is a world-leading artificial intelligence company that independently develops multimodal general big models. It has deployed MaaS (model as a service) and application-level products to empower art design, game production, film and television animation, social entertainment and other fields. In March 2023, the team adopted the native technology route and released and open-sourced the world's first multimodal model UniDiffuser based on the U-ViT architecture, successfully converting the diffusion model for the first time...

BioDigital Technology is a company founded in 2023, focusing on the development of multimodal macromodels, including a wide range of native multimodal macromodels for image, 3D and video. Their team comes from Tsinghua University's Artificial Intelligence Research Institute and other tech companies with deep technical backgrounds. The company recently closed a round of financing of hundreds of millions of dollars, which will be mainly used for R&D, product innovation and market expansion of multimodal base macromodels. BioDigital has made a series of important achievements in the multimodal field, including the development of the world's first multimodal diffusion based on the Diffusion Transformer architecture...