Apolinário Passos
Machine Learning Art Engineer at pata - data analysis and visualisation
Barcelona, Catalonia, Spain
Summary
🤩
Rockstar🎓
Top SchoolApolinário Passos is a Machine Learning Art Engineer based in Barcelona with 13 years of multidisciplinary experience blending ML, data visualization and creative technology. Currently at Hugging Face, he contributes to high-profile open-source projects like Diffusers and Hugging Face notebooks, improving training pipelines and tooling for generative models such as Stable Diffusion XL and textual inversion. He also runs apolinar.io and founded pata, applying ML and data-driven design to client work across agencies and civic projects, and has led product and tech teams at World Data Lab and political campaigns. Comfortable at the intersection of research, engineering and creative strategy, he combines hands-on model fine-tuning (LoRA, optimizers, WebUI integration) with a knack for turning complex data into compelling visual narratives.
13 years of coding experience
7 years of employment as a software developer
University of California San DiegoHigh School, High School at Centro Educacional SigmaMOOC, Visualização de Dados e d3.js, MOOC, Visualização de Dados e d3.js at UdacityHigh School, High School at Centro Educacional Moisés BertoniInterrupted Bachelor's degree, Computes Sciences, Interrupted Bachelor's degree, Computes Sciences at Universidade de BrasíliaGenerative Art and Computational Creativity, Generative Art and Computational Creativity at Simon Fraser UniversityCopyrightX, Law and Technology, CopyrightX, Law and Technology at Harvard UniversityUniversity of São Paulo
Portuguese, English, Spanish
Github Skills (20)
notebook10
pytorch10
inversion10
python10
huggingface-hub10
diffusion-models10
machine-learning10
stable-diffusion10
diffusers10
diffusion-probabilistic-models10
textual10
diffusion-probabilistic10
huggingface10
deep-learning10
trainings10
Programming languages (13)
Github contributions (5)
huggingface/diffusers
Jul 2022 - Jan 2023
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Role in this project:
ML Engineer
ML EngineerContributions:64 reviews, 12 commits, 45 PRs in 6 months
Contributions summary:Apolinário contributed to the Hugging Face Diffusers repository, focusing on model and pipeline updates. They made several updates to documentation, including model cards and quickstart guides, specifically referencing the Stable Diffusion XL models. The user modified codebase related to DeepFloyd IF, updating model names and file paths. Additionally, the user introduced changes to the training scripts, encompassing areas such as LoRA integration, WebUI support, and Prodigy optimizer configurations, demonstrating a focus on fine-tuning and enhancing machine learning model training workflows.
pytorchartdeep-learningimage2imagestate-of-the-art
huggingface/notebooks
Sep 2022 - Oct 2022
Notebooks using the Hugging Face libraries 🤗
Role in this project:ML Engineer
ML EngineerContributions:22 commits, 3 PRs, 25 pushes in 1 month
Contributions summary:Apolinário contributed to a notebook focusing on textual inversion for Stable Diffusion using the Diffusers library. Their primary contribution was adding and fixing code related to training new concepts and uploading them to a public library. They made changes to the notebook involving token access, file paths, and README generation to facilitate concept saving, uploading, and discoverability within the Hugging Face ecosystem.
nlpdeep-learningmachine-learninghugging-facenotebooks
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.