Ondrej Texler
Principal Research Scientist at Valka.AI
Los Angeles, California, United States
Summary
👤
Senior🎓
Top SchoolOndrej Texler is a Principal Research Scientist based in Los Angeles with eight years of deep expertise in generative AI, neural rendering, and photoreal virtual humans. He leads core avatar research at Valka.ai after driving revenue-generating avatar and deferred neural rendering work at HeyGen and building end-to-end text-to-video and stylized animation frameworks at Drip.Art. His background spans industry leaders (Samsung Research, Adobe, Snap) and combines GANs, transformer- and diffusion-based models, and audio-driven motion modeling to make expressive, human-centric video models. A PhD-trained computer scientist, he pairs rigorous research with product-focused delivery—shipping novel rapid-training schemes and real-time style-transfer systems that moved prototypes into production. Less obvious: he bridges low-level graphics and large-scale generative modeling, enabling both real-time portrait stylization and high-fidelity avatar pipelines.
8 years of coding experience
10 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Czech Technical University in PragueDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Faculty of Electrical Engineering, Czech Technical University in PragueMathematics and Physics, Mathematics and Physics at Gymnázium Christiana Dopplera
English, Czech
Github Skills (27)
image-synthesis10
generative-adversarial-network10
style-transfer10
siggraph10
google-colaboratory10
pytorch9
image-generation9
deep-learning9
google-colab9
neural-style-transfer9
jupyter-notebook6
multi-gpu6
seq2seq6
tensorflow5
algorithm4
Programming languages (4)
Github contributions (5)
OndrejTexler/ebsynth
Aug 2018 - Mar 2020
Fast Example-based Image Synthesis and Style Transfer
Contributions:12 commits, 9 pushes in 1 year 6 months
image-synthesisstyle-transfer
OndrejTexler/Few-Shot-Patch-Based-Training
Aug 2020 - Apr 2021
The official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training
Contributions:16 commits, 1 PR, 12 pushes in 8 months
siggraphdeep-learninggenerative-adversarial-networkstyle-transfergan
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.