Asianfin -- Beijing-based Shengshu Technology announced on Wednesday that its AI-powered text-to-video tool, Vidu, now includes a new feature allowing users to generate videos by combining images. Previously, Vidu enabled users worldwide to create 8-second videos based on written prompts. In February, OpenAI, the creator of ChatGPT, revealed its Sora model, capable of generating one-minute videos from text. However, Sora has not yet been made publicly available. The new feature of Vidu allows users to combine three images — such as a shirt, a person, and a moped — to generate a video where the person wears the shirt and rides the moped through a scene, according to Shengshu. While other platforms claim to transform text or images into videos using AI, the quality of the output varies. Shengshu's innovation, however, lies in its ability to integrate three distinct images into a cohesive, visually consistent AI-generated video. “Early on, we identified visual consistency as a challenge, and we focused on solving it effectively,” said Fan Bao, Chief Technology Officer at Shengshu.