Beijing, Oct. 27, 2026 (GLOBE NEWSWIRE) -- Vidu, the AI video platform, has reached a significant milestone in AI-powered filmmaking. Its technology supported SANXINGDUI, the first hyper-realistic AI feature film with an entirely AI-generated cast to earn a theatrical release permit and open nationwide across China.
Produced by Bona Film Group with technical support from Vidu, the 100-minute science-fiction feature was created without physical actors or digital replicas of existing performers. This milestone demonstrates how AI video technology can support feature-length storytelling at a commercial scale.
“Advanced video models shouldn’t just look good in curated demos,” said Yihang Luo, co-founder and CEO of GensPI. “Our teams and Bona Film Group formed a joint working group to tackle the key challenge of bringing AI visual creation from small-screen experiences to feature-length cinematic production. The theatrical big screen is ultimately the highest standard for visual quality, and projects like SANXINGDUI demonstrate how far AI video technology has come while giving creators the freedom to keep iterating and chase the perfect shot.”
Vidu’s role in SANXINGDUI highlights how AI video technology is helping advance the industry’s exploration of large-screen AI filmmaking. The project demonstrates how emerging AI tools can support new approaches to cinematic production and expand creative possibilities for filmmakers and studios.
Separately from the SANXINGDUI project, Vidu recently introduced Vidu Q4 Preview, the first public preview of its newest AI video model. The model supports up to 15 image references and three audio references, synchronized audio-video generation and output up to 4K resolution, highlighting Vidu’s continued focus on giving creators greater control over AI-generated video. Designed for creators, studios, brands and agencies working on narrative and commercial projects. It is available now at platform.vidu.com. For more information about the model’s capabilities and availability, see the GlobeNewswire announcement from October 7.
###
About Vidu
Vidu is a cutting-edge AI video generation model developed by GensPI, a leading Chinese generative AI company. Built by a team from Asia's top-ranked Tsinghua University, the technology is part of the company's effort to build the world's first general world model to unify the digital and physical worlds. Guided by first-principles thinking, it uses visual and auditory information to train its foundation world model, enabling modeling, reasoning, predicting, and acting upon the rules of both worlds, and ultimately, AGI. Vidu has grown into a global platform, and public reports show its developer has raised nearly RMB 6 billion (approximately $890 million USD) since February 2026.
Croft McLean RLF Communications // GensPI cmclean@rlfcommunications.com 252.646.9865
