Yuri Viazovetskyi

I'm a machine learning engineer at Aiuta in Limassol, where I primarily focus on virtual try-on using diffusion models. Previously, I worked on portrait stylization at Prisma Labs. Earlier in my career, I experimented with generative adversarial networks at Yandex.

Email  /  CV  /  Scholar  /  Github  /  Twitter  /  LinkedIn  /  Telegram

profile photo

Projects
Virtual try-on
Aiuta, 2023
App Store / Google Play / Instagram

Lensa AI: Magic Avatars
While working at Prisma Labs, 2022
Project page / ProductHunt / TechCrunch / Time / CNN

Lensa AI: Magic Avatars uses the Stable Diffusion to generate artistic avatars from user selfies.

Research
StyleGAN2 Distillation for Feed-forward Image Manipulation
Yuri Viazovetskyi, Vladimir Ivashkin, Evgeny Kashin
ECCV, 2020
code / arXiv

Paired image-to-image translation trained on synthetic data outperformed prior approaches in image manipulation