Eduardo Pelegrín
Madrid, Community of Madrid, Spain
Summary
🤩
Rockstar🎓
Top SchoolEduardo Pelegrín is a Madrid-based machine learning engineer with six years of experience focused on practical AI and model optimization. He has contributed to the prominent InvokeAI project, improving Stable Diffusion performance and memory behavior on Apple M1/MPS hardware and integrating advanced features like textual inversion. Currently pursuing dual master's degrees in Artificial Intelligence and Computer Engineering at Universidad Politécnica de Madrid, he pairs academic rigor with hands-on open-source work. Known for squeezing better performance from constrained devices, he bridges research-level techniques and production-minded engineering.
6 years of coding experience
Master's degree, Artificial Intelligence, Master's degree, Artificial Intelligence at Universidad Politécnica de Madrid
Github Skills (18)
pytorch10
artificial-intelligence10
python10
metal-performance-shaders10
attention-mechanism10
machine-learning10
stable-diffusion10
mps10
image-generation9
optimization9
cuda9
ai-image8
ai8
generative-art8
inversion7
Programming languages (7)
Github contributions (5)
invoke-ai/InvokeAI
Sep 2022 - Oct 2022
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
Role in this project:
ML Engineer
ML EngineerContributions:28 reviews, 14 commits, 17 PRs in 29 days
Contributions summary:Eduardo primarily focused on optimizing and adapting the Stable Diffusion model for various hardware configurations, particularly Apple's M1/MPS architecture. The commits include performance improvements to attention mechanisms, the core computational component of Stable Diffusion, and modifications to the code to handle memory constraints on different devices. Further contributions address reproducibility issues and integrate textual inversion techniques, demonstrating a focus on model stability and advanced features.
serveswebuioutpaintingdiffusionlatent-diffusion
Any-Winter-4079/Transformer_Robot
Jan 2024 - Apr 2025
Contributions:313 pushes, 5 branches in 1 year 2 months
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.