Vadim Epstein
Visual Artist at Christoph Winkler Company
Brighton, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolVadim Epstein is a Brighton-based visual artist and creative technologist with 11 years of experience blending digital art, AI/ML, and a strong foundation in theoretical and mathematical physics. He has produced over 230 live visual performances, led more than 150 multimedia projects as a studio director, and designed courseware and masterclasses for artists and professionals worldwide. Technically fluent, he builds generative and interactive systems—his open-source work includes a CLIP + FFT/DWT/RGB text-to-image/video tool that added multi-language support, style transfer, and video output. He has collaborated with leading studios and art institutions (Refik Anadol Studio, Sila Sveta) on GAN control and latent-space exploration for museum-grade installations. As a teacher and mentor, he translates complex AI concepts into practical creative workflows, a skill informed by his early IT career at HP and advanced physics training. Unusually, his practice bridges large-scale production management and low-level algorithmic experimentation, making him equally at home on stage, in the studio, or in code.
11 years of coding experience
19 years of employment as a software developer
Master's degree, Theoretical and Mathematical Physics, Master's degree, Theoretical and Mathematical Physics at MISiS
English, Russian
Github Skills (15)
fftw10
video-production10
video-editing10
text-to-image10
fft10
machine-learning10
pytorch10
video-encoder10
clip10
video-conversion10
python10
image-processing10
deep-learning8
nlp8
data-science8
Programming languages (6)
Github contributions (5)
eps696/aphantasia
Feb 2021 - Sep 2022
CLIP + FFT/DWT/RGB = text to image/video
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:6 releases, 157 commits, 2 PRs in 1 year 6 months
Contributions summary:Vadim appears to be primarily responsible for the initial setup and implementation of a text-to-image/video tool using CLIP and FFT/DWT methods. The initial commit establishes the core framework, while subsequent commits introduce features such as style transfer functionality, multi-language support, and depth processing capabilities. The user demonstrated a strong understanding of the project's underlying technologies by integrating improvements in the core image generation pipeline and by creating a video output.
dwttext-to-videocliptext-to-imagefft
eps696/SD
Jan 2023 - Mar 2023
Contributions:1 release, 12 commits, 9 pushes in 1 month
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.