With professional quality output, high efficiency, and flexible creative scenarios, the new Vidu Agent enables users to generate complete 15 to 30 second video with a single click.
SINGAPORE, Dec. 16, 2025 /PRNewswire/ — ShengShu Technology, a global leader in multimodal generative AI, today announced the launch of Vidu Agent, a one-click professional video creation tool designed to turn images into complete, platform-ready videos in minutes. By integrating creative planning, shot sequencing and automated assembly into a single workflow, Vidu Agent enables creators, brands, and marketers to produce professional quality video content with high efficiency and minimal manual input.
Vidu Agent is positioned as a one click video creation partner that supports a wide range of content formats, including advertisements, TVCs, music videos, remakes, and short narrative clips. With just a single click, users can move directly from visual reference to a finished 15 to 30 second video optimised for major streaming and short-form platforms.
“AI video creation is increasingly moving beyond raw generation quality toward real production workflows,” said Yihang Luo, CEO of ShengShu Technology. “Vidu Agent automates the steps between visual input and a finished video, helping users produce structured, polished content with far less effort. Our focus is on making video creation more intuitive, efficient and accessible across creative and commercial use cases.”
From Image Input to Finished Video in Minutes
Vidu Agent supports both single image and multiple image inputs, allowing users to upload up to seven images to guide video generation across different subjects, perspectives or product angles. The system recognises single, two- and three-view references and maintains strong consistency in product features and subject identity throughout the video, even across longer sequences, ensuring that key visual details remain stable and accurate.
Once images and a short description are provided, Vidu Agent automatically generates a script, structures the narrative and assembles a complete 15 to 30 second video suitable for major platforms. Script generation typically completes within one minute, and the full workflow is usually finished in around three minutes. The platform currently supports up to two video tasks at a time, balancing speed with creative throughput.
Built for Professional Production and Real-World Creative Scenarios
Vidu Agent is designed to deliver professional quality video output while significantly reducing the complexity of traditional production workflows. By combining imaginative content generation with shot-level controllability, and fine-grained editing logic, the system automatically assembles videos with coherent structure and pacing that mirror professionally produced content. This enables both individual creators and commercial teams to produce polished videos efficiently, without specialised production expertise.
Efficiency and scalability are central to the design of Vidu Agent. Through a single-click workflow, it supports rapid creation, template-based reproduction and batch production, allowing users to generate consistent output at speed and at lower cost. These capabilities make Vidu Agent well suited to high-volume production environments where turnaround time, output consistency and cost control matter.
At the same time, the Agent is optimised for scenario-based creative use, supporting plot-driven storytelling, commercial advertising, music videos and short-form creative content. By structuring output around recognisable creative scenarios, Vidu Agent provides clearer application pathways for AI-generated video across different formats and industries.
One of the most immediate applications is e-commerce and advertising production. By uploading one or more product images and adding a concise product description, users can generate a complete 15 to 30 second commercial video aligned with the length and format requirements of major platforms. The ability to use multiple images allows advertisers to showcase products from different angles or highlight specific features, supporting richer creative variations and faster iteration across campaigns.
The launch of Vidu Agent reflects ShengShu’s broader effort to translate advances in multimodal AI into tools that support real-world creative work. It follows a series of recent releases, including Vidu Q2’s Reference-to-Video, which introduced high-consistency performance driven video generation, and the expansion of Q2 into full image generation with professional quality editing capabilities. Together, these updates demonstrate ShengShu’s strong technical foundation and rapid iteration in multimodal AI. By integrating automation, consistency and scenario driven output into a single experience, Vidu continues to expand its role in modern content production.
Vidu Agent will enter global beta on December 16. Users can apply to join the community for early access. It is also available via the Vidu Agent API at platform.vidu.com.
To learn more about Vidu, please visit www.vidu.com
About ShengShu Technology
Founded in March 2023, ShengShu Technology is a world-leading artificial intelligence company, specializing in the development of Multimodal Large Language Models. Driven by innovation, the company delivers cutting-edge MaaS and SaaS products that revolutionize creative production by enabling smarter, faster, and scalable content creation. With its flagship video generation platform Vidu, ShengShu Technology’s solutions have reached more than 200 countries and regions around the world, spanning fields including interactive entertainment, advertising, film, animation, cultural tourism, and more.
SOURCE ShengShu Technology