Vidu AI, a generative artificial intelligence video platform developed by Chinese company Shengshu Technology, today announced an update to its latest Q1 model, featuring advanced “reference to video reference” functionality with semantic understanding.
The company is developing a generated video AI model that competes with Openai's SORA, which can create vivid video sequences. This update allows for a rich video context for the creation of video scenes containing multiple elements that remain the same between frame-to-frame clips.
Users can upload up to seven reference images and include prompts that combine prompts for AI to use in the scene. For example, AI will use what a company calls “semantic understanding” to reference images, associate them with text prompts, and infer missing elements to generate key objects.
“This update will break through the limits of what creators think they can do with AI videos,” said CEO Luo Ihan. “The user is now able to create fully realized scenes, complete with detailed casting of characters, objects and backgrounds by magnifying the multi-image referenced to support up to seven inputs.”
For example, users can upload images of a green dress, an idyllic forest scene, and a young woman with an owl. Next, enter the prompt. “The woman plays the violin in the forest, and an owl jumps down and lands on a branch near the sunrise.”
Yihang said the Vidu Q1 Semantic Core Engine will generate a violin in her hand, maintaining scene consistency and story quality throughout the clip. Using this technology, creators no longer have to face sudden technical hurdles when trying to create complex scenes. You will need a text prompt and an image when creating a consistent video scene.
Vidu is competing with Google LLC's VEO 3, which was released in late May. Its generated video features include natural English prompts and reference images along with a filmmaking tool called Flow. This allows users to manage narrative designs and develop an entire film generated in short AI, including audio including visuals, special effects and audio.
Shengshu announced a partnership with Los Angeles-based animation studio Aura Productions in late March, releasing a 50-episode short film sci-fi animated series that was fully generated by AI. The project is attempting to redefine digital entertainment by using AI capabilities to enhance traditional narrative techniques. It will be released across major social media platforms this year.
“AI is no longer just a tool. It's a creative reinforcement that allows production to be expanded while maintaining artistic integrity,” Aura showrunner DT Carpenter told Variety about the project.
Image: Vidu AI
Support open-free content by sharing and engaging with the content and the community.
Join TheCube Alumni Trust Network
Sharing where technology leaders connect, sharing intelligence and creating opportunities
11.4k+
Cube Alumni Network
C level and technology
Domain Experts
Connect with over 11,413 industry leaders from a network of high-tech and business leaders that form their own trustworthy network effects.
SilicOnangle Media is a leader in digital media innovation serving innovative audiences and brands, bringing cutting-edge technology, impactful content, strategic insights and real-time audience engagement. As the parent company of Silicon angle, TheCube Network, Research on TheCube, Cube365, TheCube AI TheCube Superstudios, including those founded in Silicon Valley and the New York Stock Exchange (NYSE). It works at the intersection of media, technology, and AI. .
Founded by Tech Visionarys John Furrier and Dave Velante, Siliconangle Media is a reach of over 15 million elite technical experts and builds a strong ecosystem of industry-leading digital media brands. The company's new and unique TheCube AI video cloud is based on audience interactions. Leveraging TheCubeai.com neural networks, we help technology companies make data-driven decisions and stay at the forefront of industry conversations.
