Alexander Brown
Senior Software Engineer at ComfyUI
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlexander Brown is a Senior Software Engineer with 13 years of experience building testing tools and developer-facing systems, most recently contributing to AI-focused UI work at ComfyUI and founding frontend efforts at a startup. He spent a decade at Google developing maintainable Java and TypeScript/Angular code, mentoring teams and balancing customer needs with great developer experience. A hands-on open-source contributor, he has improved interfaces for prominent generative image projects and enhanced ML tooling for VQGAN-CLIP and Big Sleep, adding usability features like video export and progress feedback. With dual degrees in Computer Science and Linguistics from the University of Arizona and roots in multimedia support and research programming, he brings an unusual mix of product empathy, UX polish, and experimental ML experience to engineering problems.
13 years of coding experience
12 years of employment as a software developer
The University of ArizonaGraduate Leadership Mountain View, Graduate Leadership Mountain View at Mountain View Chamber of CommerceDesert Mountain
English
Github Skills (17)
pytorch10
text-to-image10
javascript10
artificial-intelligence10
python10
image-processing10
css10
machine-learning10
generative-adversarial-network10
text2image10
deep-learning10
computer-vision10
ui-design9
stable-diffusion9
webui8
Programming languages (14)
Github contributions (5)
lucidrains/big-sleep
Jan 2021 - Feb 2021
A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
Role in this project:
ML Engineer
ML EngineerContributions:16 commits, 4 PRs, 6 comments in 3 days
Contributions summary:Alexander primarily contributed to the `big-sleep` repository, a tool for text-to-image generation. Their work focused on improving the image generation process by integrating progress bars for better user feedback. They also added features for experimental resampling and modified the training loop. Additional commits include optimization of the loss reporting and improvements to versioning.
pytorchcommand-line-tooldeep-learningbigganclip
nerdyrodent/VQGAN-CLIP
Jul 2021 - Jul 2021
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
Role in this project:ML Engineer
ML EngineerContributions:9 commits, 3 PRs, 1 comment in 1 day
Contributions summary:Alexander primarily focused on modifying and enhancing the `generate.py` script, likely the core execution file for the VQGAN-CLIP model. Their commits included adding initial image and noise options, integrating different optimizers (Adam, AdamW, etc.), and incorporating video creation functionality with ffmpeg. Furthermore, they modified the code to add prompts as metadata to the output images and videos. These changes suggest the user was working on model configuration, experimentation, and usability improvements.
pytorchstylegandeep-learningclipcomputer-vision
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.