Vidu AI, a generative artificial intelligence video platform developed by Chinese firm ShengShu Technology, today announced an update to its latest Q1 model featuring an advanced “reference-to-video” feature powered by semantic understanding.
The company is developing a generative video AI model that competes with OpenAI’s Sora, which can produce vivid video sequences. The update allows for richer video context for the production of video scenes involving multiple elements that remain the same between clips from frame to frame.
Users can now upload up to seven reference images and include a prompt that combines them for the AI to use in a scene. For example, the AI uses what the company calls “semantic understanding” to reference the images and relate them to the text prompt and even infer missing elements to generate key objects.
“This update breaks through the limits of what creators thought they could do with AI video,” said Chief Executive Luo Yihang. “We’re getting closer to enabling users to create fully realized scenes, complete with a detailed cast of characters, objects, and backgrounds, by expanding multi-image referencing to support up to seven inputs.”
For example, a user could upload an image of a young woman in a green dress, an idyllic forest scene and an owl. Then input the prompt: “The woman plays the violin in the forest while the owl flies down and lands on a nearby branch at sunrise.”
Yihang said the Vidu Q1 semantic core engine will generate a violin in her hands, preserving scene consistency and narrative quality throughout the clip. Using this technology, creators no longer need to face steep technical hurdles when attempting to create complex scenes. A text prompt and images are all they need when producing consistent video scenes.
Vidu is competing with Google LLC’s Veo 3, released in late May. Its generative video capabilities include natural English prompts and reference images alongside a filmmaking tool called Flow, which allows users to manage narrative design to develop entire short AI-generated films that include visuals, special effects and audio, including speech.
ShengShu announced a partnership with Los Angeles-based animation studio Aura Productions in late March to release a 50-episode short film sci-fi anime series fully generated by AI. The project seeks to redefine digital entertainment by using AI capabilities to augment traditional narrative techniques. It is slated for release across major social media platforms this year.
“AI is no longer just a tool; it’s a creative enhancement that allows us to scale production while maintaining artistic integrity,” said D.T. Carpenter, showrunner at Aura, told Variety about the project.
Image: Vidu AI
Support our open free content by sharing and engaging with our content and community.
Join theCUBE Alumni Trust Network
Where Technology Leaders Connect, Share Intelligence & Create Opportunities
11.4k+
CUBE Alumni Network
C-level and Technical
Domain Experts
Connect with 11,413+ industry leaders from our network of tech and business leaders forming a unique trusted network effect.
SiliconANGLE Media is a recognized leader in digital media innovation serving innovative audiences and brands, bringing together cutting-edge technology, influential content, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — such as those established in Silicon Valley and the New York Stock Exchange (NYSE) — SiliconANGLE Media operates at the intersection of media, technology, and AI. .
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a powerful ecosystem of industry-leading digital media brands, with a reach of 15+ million elite tech professionals. The company’s new, proprietary theCUBE AI Video cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.