With all the things that are going on in the world, sometimes we wish that we could be anime characters. Well, now you can: you simply upload a selfie to the Selfie 2 Waifu website and it turns you into a “waifu.” In case you don’t know what a waifu is, it’s a word used in Japanese otaku culture that means “wife.” If someone’s your waifu, they’re your crush.
Bored Panda spoke with Japan-based programmer Creke who created the Selfie 2 Waifu website. According to them, they're anime movies and comics fan, as well as an otaku who works as an engineer during the day developing high-throughput distributed systems and computer vision engineering.
“I happened to know there is an algorithm called UGATIT which is good at making selfies into cartoon characters, or waifu if you like, whose authors I want to thank for their beautiful algorithm. So I combined the algorithm and my engineering skills and made it into an easy-to-use website so that everyone can get access to this fascinating magic,” Creke told us. Scroll down for the rest of our interview with them about the character design upgrades they're working on, as well as privacy concerns.
Creke told us that they've been busy these past few weeks improving Selfie 2 Waifu after work. “I divided the optimization work into 3 parts: refactoring architecture, improving computing performance, and reducing server error rate,” they said.
The programmer went into detail about their process: “In the first version, I put everything into one module just to make it simply work. As users increased, the error rate was increasing, too. Then I split the web frontend and computing backend as independent modules and made a distributed architecture. Then we could do the ‘more users, more machines’ trick.”
They continued: “Soon I realized that GPU servers are far too expensive, my credit card bills were flying like a rocket. So I gotta dive deep into the computing principle level, in order to save some money. As a result, a pre-fork multi-worker pipeline was built where GPU concentrates in model inferencing and CPU does the image decoding and resizing job.”
However, Creke admitted that they didn’t save money by doing this because every time the server performance got optimized, they got more visitors coming to their website, wanting to turn themselves into anime heroes. “But I'm glad I managed to host 3 or 4 times the audience by adding 1.5-2 times [the number] of machines, and the servers are running at a low error rate. Well most important of all, I'm so happy that you guys are enjoying it, that's all that matters.”
We also spoke to the programmer about privacy concerns. Here’s what they had to say: “For the algorithm, I am just using the pre-train model of UGATIT. The dataset of the official model is trained using 3,400 photos and 3,400 anime drawings from public dataset. Indeed, I want to finetune the model, 'cause now shadow makes some bad cases. But since I cannot collect any users' selfies from the site without their permission which results in short training data, the original model is still being used. So I have to optimize the post-process procedure of these cartoon drawings as much as I can.”
For the best results, it’s advised that you submit a passport-style photo with a plain background. While the website can turn anyone into an anime character, it works best with female selfies, just like the name of the website suggests. Keep in mind that you can get slightly different results if you upload the same photo twice, so if you decide to become a waifu, try it out a few times.
The online waifu tool is based on a 2019 paper by South Korea’s Clova AI Research, gaming company NCSOFT, and the Boeing Korea Engineering and Technology Center, titled "Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation." If it sounds complicated, it really is.
Some people also had fun by posting pictures of celebrities and pop culture characters instead of their own photos to see how the Selfie 2 Waifu tool responds. Some of the results are absolutely hilarious.