Chinese Student Develops AI That Transforms Photos Into Anime [Video] | AsianCrush

Welcome to the website of sports pharmacology!

Features of the use of steroids. Every modern person has to decide for himself how he sees his own body and what he wants to achieve with the help of balanced nutrition and training. Since many of us are maximalists, we are used to set high goals. These are the athletes who strive to do everything faster or more buy anabolic steroids efficiently than their rivals in the competition. It is impossible to achieve such a result without a comprehensive approach. In order not to have to regret not quite an impressive result, it is better to combine grueling exercises with taking special drugs that can improve their effectiveness.

Achieving a lofty goal. Today, anabolic steroids are a common type of pharmacology that athletes take. These drugs allow you to beat the competition and to install put before you. It is only necessary not to forget about the rules and doses of their use to minimize the risk of negative factors. High-quality sports pharmacology makes it possible to make the muscles more dense, as well as to increase the relief of the body.

Anabolic steroids

The use of such drugs in the modern world is not a novelty. They have been known for several decades, so more than one generation of athletes was able to achieve excellent results through their use. A bodybuilder just needs to know where to buy steroids. Such products are offered by many companies today, but only some of them can guarantee really high quality of the presented products. Correct dosage of these drugs will help at all to eliminate the side effects. If you need a first-class sports pharmacology, feel free to contact us and get the opportunity to purchase such substances. With their help, the body will be maintained in perfect condition without harm.

Variety of drugs. The use of special means allows athletes to achieve important goals. Some athletes decide to buy steroids in order to increase muscle mass. Another use of drugs allows you to get rid of fatty tissues that interfere with the creation of a beautiful figure. To increase the weight, you should use:

Steroids Online
Internet Love

Chinese Student Develops AI That Transforms Photos Into Anime [Video]

Katie Cannon June 13, 2018 August 20th, 2019

We all know that AI will inevitably take over the world, bringing humanity to its knees by the power of our own creation–but for now, it’s settled for making inroads in the wonderful world of Japanese anime.

Artists have long since been partaking in nijigenka, or “2D-ification,” taking pictures of real life people and transforming them into anime characters.  Just as we might all like comparing our fave anime characters to the actors who might play them in real life, it can be just as fun to reimagine what flesh-and-blood folks would look like as shoujo heroes. But can a robot do it better?

At recent workshop in Tokyo, Fudan University undergrad Yanghua Jin demonstrated how, using Generative Adversarial Networks (GAN) and Deep Learning (yeah, idk what any of that means either), he can create gorgeous anime portraits without wielding any artistic skill himself.

In his presentation, he explains a lot of complex math-y things that I am really too dumb to explain. But here’s what I have gathered from SoraNews24’s explanation: basically, the tech takes a two-pronged (or rather, two-networked) approach.

The first network, the generator, takes the faces of real people and translates them into anime using features like hair color and style, facial expression, etc, as well as considerations like facial proportion and body angle. The first network, the generator, takes the faces of real people and translates them into anime using features like hair color and style, facial expression, etc, as well as considerations like facial proportion and body angle. Then, after creating the new image, the second network, the discriminator, scans its library of anime images  and tries to pick out the new, “fake” anime image produced  by the generator from the original artworks.

One of the biggest difficulties is, while GAN is generally good at transferring textures, anime characters have proportions (huge-ass eyes, tiny-ass mouths) one doesn’t generally see IRL.

Since the GAN learns from its mistakes in past models (cool but terrifying), the results should only get better and better.

At first, the AI anime turned out…pretty wonky.

An otaku’s acid trip nightmare.

But thanks to ~Deep Learning~, they’ve vastly improved since.

Watch Jin’s entire presentation:

https://youtu.be/UDT_2lHv8o8