Many might be interested in an AI tool that changes your picture into a zombie with Halloween season upon us. This GAN architecture extension can generate impressively photorealistic images while enabling user control over image style. With a new release this year, NVIDIA improved StyleGAN2 with redefined state-of-the-art image generation, inspiring fun and creative pursuits with faces. StyleGAN tech-inspired the last month's viral Toonify Yourself website, created by a couple of independent developers. It turns selfies into big-eyed cartoon characters. A Nebraska-based developer Josh Brown Kramer has taken facial image transfer tech to a new height, building a zombie generator.
Doron Adler and Justin Pinkney, two software engineers, recently released a "Toonification translation" AI model that turns real faces into flawless cartoon representations. And while the toonification tool, "Toonify," was originally available to the public, it became too popular to sustain cheaply. But some people managed to Toonify a ton of celebrities before the tool was pulled, and all the animations are stellar. After much training of neural networks @Norod78 and I have put together a website where anyone can #toonify themselves using deep learning!https://t.co/OQ23p30isC In a series of blog posts, which come via Gizmodo, Pinkney outlines how he and Adler created Toonify.
Want to see what you'd look like as a zombie? Forget makeup; now there's a GAN for that. The popular StyleGAN (Style Generative Adversarial Network) is a GAN architecture extension open-sourced by Nvidia in 2019 that can generate impressively photorealistic images while enabling user control over image style. This year's new and improved StyleGAN2 has redefined the state-of-the-art in image generation -- and has also inspired a number of fun and creative pursuits with faces. StyleGAN tech inspired last month's viral Toonify Yourself website, which was created by a couple of independent developers and turns selfies into adorable big-eyed cartoon characters. Now, just in time for costume season, another indie developer has taken facial image transfer tech to the opposite end of the cuteness spectrum, building a zombie generator.
Last month, the deep learning powered online tool Toonify Yourself! Designed "for fun and amusement using deep learning and Generative Adversarial Networks," the system was developed by a pair of independent researchers, Justin N. M. Pinkney and Doron Adler, and let anyone change selfies or portraits into impressive animation-style images. Demand for the high-performance homemade model caused the site to crash, but it quickly returned thanks to support from user donations. In a paper submitted to the NeurIPS 2020 Machine Learning for Creativity and Design workshop, Pinkney and Adler present their research, which enables image generation in novel domains and with a degree of creative control on the output. The team's resolution dependant GAN interpolation method combines high resolution layers of an FFHQ model with low resolution layers from a model transferred to animated character faces to enable the combination of realistic facial textures with the structural characteristics of a cartoon.
A Seoul National University Master's student and developer has trained a face generating model to transfer normal face photographs into cartoon images in the distinctive style of Lee Mal-nyeon. The student (GitHub user name: bryandlee) used webcomics images by South Korean cartoonist Lee Mal-nyeon (이말년) as input data, building a dataset of malnyun cartoon faces then testing popular deep generative models on it. By combining a pretrained face generating model with special training techniques, they were able to train a generator at 256 256 resolution in just 10 hours on a single RTX 2080ti GPU, using only 500 manually annotated images. Since the cascade classifier for human faces provided in OpenCV-- a library of programming functions mainly aimed at real-time computer vision -- did not work well on the cartoon domain, the student manually annotated 500 input cartoon face images. The student incorporated FreezeD, a simple yet effective baseline for transfer learning of GANs proposed earlier this year by KAIST (Korea Advanced Institute of Science and Technology) and POSTECH ( Pohang University of Science and Technology) researchers to reduce the burden of heavy data and computational resources when training GANs. The developer tested the idea of freezing the early layers of the generator in transfer learning settings on the proposed FreezeG (freezing generator) and found that "it worked pretty well."