Stable Diffusion from Scratch
Convolutions, attention, VAEs, diffusion, UNet and CLIP, explained with the maths and implemented in TensorFlow. Every part builds on the one before it.
the blog
Practical AI, explained three ways: the intuition, the understanding behind it, and an implementation you can run. Deep dives come as series, read in order; everything else is a standalone article.
Multi-part deep dives. Each one is a single track you read from part 01 onwards.
Convolutions, attention, VAEs, diffusion, UNet and CLIP, explained with the maths and implemented in TensorFlow. Every part builds on the one before it.
A fast, intuitive model that scores options instead of writing text. Frozen Qwen3-8B embeddings, two small heads, contrastive learning and a three-stage training recipe, explained with the maths and rebuilt end to end.
Standalone pieces: paper notes, opinions and experiments.
No standalone articles yet. The series above is the place to start.
Every post, by year.
Nothing matches these filters.