Archive
- Learning Position — Trainable Embeddings from BERT to GPT
- Understanding Positional Encodings in Transformers
- Claude Code Power Tips
- Sparse Attention
- Limitless Video
- Still Talking?
- Tesla FSD
- Autostart Node.js Apps at Boot
- Finetuning Redpajama (OpenLlama)
- PilotWatch
- miniSD - Fast Quarter-Sized Image Generation using Stable Diffusion
- Alpaca Finetuning of Llama on a 24G Consumer GPU
- Object Detection - Part 5 Final
- Tiny ChatGPT
- Object Detection - Part 4 Multiple Objects
- Posing Heads with Stable Diffusion
- Object Detection - Part 3 Compound Loss
- Object Detection - Part 2 Bounding Boxes
- Object Detection from Scratch - Part 1
- DiffEdit - Semantic Image Editing with Stable Diffusion
- UFO Lands on Highway! Or Depth Estimation using ML
- Catch! Using Recurrent Visual Attention.
- Pong From Pixels.
- Video Search Engine Using OpenAI's CLIP
- Unleash the GPU in your Colab Notebook
- Relight.
Projects
Sandtoy
Fun little pixel toy written in WebGL using a fragment shader to do GPU accelerated particle physics.
Fun little pixel toy written in WebGL using a fragment shader to do GPU accelerated particle physics.
Stable Diffusion Poser
Control Stable Diffusion Image Generation with an Image Regression Model for Head Pose.
Control Stable Diffusion Image Generation with an Image Regression Model for Head Pose.
Share on Twitter
John Robinson © 2022-2025

