After Vidu’s multi-reference Q1 went live yesterday, Kling’s multi-reference feature will likely be updated soon as well. I’ve always believed that multi-reference is a crucial method for solving character consistency and scene consistency. This update is the first step toward completely resolving consistency issues, and within a few months, the consistency problems that plague most creators could be resolved.
It was pure luck.
Anyone who has written Chinese science fiction knows that the current Chinese sci-fi market is highly competitive, but 80% of the market belongs to Liu Cixin. The remaining 20% is usually unread by anyone. There are few opportunities and intense competition, and readers are nowhere to be found. Therefore, many science fiction authors are confused, even paralyzed by uncertainty.
After completing this week’s work, next week I’ll start producing “The Withered Sea Project.” This novel adaptation is being prepared for this year’s Vacat Award, and it’s more suitable than my previous work, “The Resolve,” because this is a Chinese-style science fiction story. At the same time, that one was a steampunk story. “The Withered Sea Project” takes place in the Xinglong Civilization, which represents China in the computational universe.
AI technology is in a phase of rapid development, with most AI film technologies having primary update cycles of just 3 months or even shorter. This means that the technology mastered today will likely be obsolete within a few months. Films produced today may become unwatchable within a matter of months.
A friend of mine assembled a team and asked me about the difficulties I’ve encountered when producing AI films, as they want to research these issues from an academic perspective. This is challenging because the current technical problems are all major ones that small teams may not necessarily have the opportunity to solve. In fact, all the difficulties are concentrated around consistency issues.
A polymath is someone who possesses deep knowledge across multiple disciplines and can think across fields – a generalist of sorts. Sometimes also called a Renaissance person.
Recently, several friends have told me they don’t want to make bad films in the AI era, and I’ve always felt the same way. Although AI films aren’t rated on Douban, I don’t want to open Douban one day and see my movie scored at 3-something. Or have it start with all praise, only for real audiences to angrily give it 1-star ratings after watching – that kind of book or film.
The short story and film production of “The Resolve” has come to an end. A new film is already on the horizon. I originally planned for “The Resolve” to participate in the Vacat Award. Still, I’ve now decided that the second film, “The Whithered Sea Project,” will be the one to join in the Vacat Award.
The development of any new phenomenon is fraught with twists and turns – old eras, old things, and conservative people all create obstacles. As a new form of artistic expression, AI naturally encounters various predicaments. AI doesn’t just have its cool aspects; dark clouds loom over it.
My WeChat article “In the AI Era, One Person is an Entire Film Crew” has encountered some questioning voices these past few days. Therefore, although I’ve already written “Current Limits of AI Filmmaking,” I still want to discuss today what AI can and cannot do.