Shengshu

Shengshu is an AI research company focused on generative video technology. The lab is behind the Vidu family of models, which target high-quality video synthesis from both text and image inputs. Their work positions them among a growing cohort of organizations pushing the boundaries of AI-driven video creation. On Venice, Shengshu offers two video generation models under the Vidu Q3 name, both released in January 2026. One handles text-to-video generation, producing video clips from descriptive prompts, while the other supports image-to-video synthesis, animating still images into motion sequences. Together they provide complementary entry points for video creation workflows. Shengshu's exclusive focus on video generation distinguishes it from broader multi-modal labs. By shipping both text-to-video and image-to-video capabilities under a single model generation, the lab offers a cohesive toolkit for creators looking to bridge static and dynamic media.