iQIYI Reconstructs Lost 1938 Film Using NadouPro – Unite.AI AI Workflow
A team of eight used iQIYI’s NadouPro platform to reconstruct a 1938 film whose prints, reels and scripts were lost, the company announced on November 6, 2026. The short film, completed in two months, was shortlisted for the Future Images AI Unit 2026 at the 39th Golden Rooster Awards.
The team worked at the iQIYI-XMU Joint Film Restoration Laboratory. Its task was different from conventional restoration, which uses digital technology to repair damage and improve image quality in surviving material. Visiting Shanghai after sixty years it had been lost for nearly 90 years, leaving photographs, posters and newspaper clippings as conceptual guides for generating a new version.
iQIYI describes the original as one of China’s first science fiction works, a comedy that imagined life sixty years in the future.
Zidong Jiang, a member of the joint laboratory and director of iQIYI’s artificial intelligence restoration technology, said the team then pursued a creative reconstruction based on available historical materials rather than attempting to restore a surviving print.
Fixed digital asset continuity issue
The production highlighted two central difficulties in generative video: maintaining coherence of characters in scenes and achieving precise camera control. The story spans from 1938 to 1998 and features multiple characters, requiring continuity across eras as well as individual shots.
NadouPro served as a centralized production hub. The team adjusted digital assets for each character’s facial features, proportions and costumes before generating subsequent shots from those foundational files, rather than creating each character again for each scene. iQIYI says this process kept the characters’ looks consistent throughout the film.
3D Director Studio supports director control
Recreating performances from still photographs required detailed control over the images generated. NadouPro’s 3D Director Studio allowed the team to adjust character positioning, composition and movement, with additional tools for testing scenes, visual styles and camera angles.
Director Enji Yang credited the platform with helping the team move from relatively casual image generation to shooting with clear directorial intent. Early production work still followed conventional steps: script analysis, character design, scene design, and storyboard planning. “We always believe that the audiovisual design of a film should take priority, before considering how AI can make it happen,” Yang said.
The filmmakers gave the two eras distinct visual treatments. The 1938 sequences took inspiration from early black-and-white cinema through steady camerawork and vintage lighting, while the 1998 scenes adopted natural light and handheld camera movement in a documentary style.
Previous restoration work informs the reconstruction
iQIYI has been exploring film restoration via artificial intelligence since 2017. Its proprietary ZoomAI uses algorithms for scratch repair, super resolution, noise reduction and intelligent frame interpolation. The company says these features help move recovery from manual frame-by-frame work towards automated processes. Through its joint laboratory with Xiamen University, iQIYI has already brought a number of classics back to 4K screens.
Aigong Zhang, chief planner of the short film and director of the joint laboratory, described the project as an integration of traditional film craftsmanship with artificial intelligence. This combination is visible in a workflow where historical documents and conventional preproduction guide creative choices, while NadouPro provides tools to generate and control images.
The project extends iQIYI’s restoration work into a different category. Fixed character resources and explicit directorial controls solve practical production problems, but the surviving archive still defines what can be reconstructed. The resulting short film is a new interpretation guided by historical evidence; does not recover the lost original footage.



Post Comment