The tech industry has continued to make strides to develop artificial intelligence programs to help with the anime production workload. Dwango’s Yuichi Yagi debuted an AI program that creates in-between animation in 2017. Dwango then announced the program was utilized for some parts of FLCL Progressive. Imagica Group and OLM Digital joined forces with the Nara Institute of Science and Technology (NAIST) to develop a technique for automatic coloring, further expanding AI options.
The manga publisher Hakusensha has begun using PaintsChainer automatic coloring program for some of its online manga releases.
Video game company NCSoft (Guild Wars 2) researchers Jun-Ho Kim, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee introduced a program that uses Generative Adversarial Networks (GANs) to transform real-life people into anime characters. The researchers released the program code on Github and published a research paper detailing their findings.
The research team expanded tests of its technology to include species swapping and create museum-worthy portraits.
Admittedly, the program’s results still needs to keep “learning” if we can hope to get anime character designs anywhere near a professional level, but it’s off to an impressive start.
The program MakeGirls.moe will also auto-generate anime character portraits, but bases its results on selection by the user. Its results have greatly improved since the first time I tried it out in 2017.