← All projects

ML

Nano-Catana

Custom diffusion image models trained on 100k+ cat pictures

Lightning AIPythonPyTorchWanDBGPU nodes

TLDR

I have got my hands on a couple of GPUs ranging from NVIDIA L40S to H100s. I have scraped a dataset of 100k+ cat pictures, annotated them using Qwen llm's and trained a couple of diffusion models from scratch. The models are trained on 512x512 images and can generate high quality cat images. The models are trained using Lightning AI and PyTorch. While really silly and not the most useful project, it was an awesome way to learn about image diffusion, training models from scratch and managing training runs across multiple GPU clusters.

Picture of generated cats using Nano Catana 0.1
Generated cats using Nano Catana 0.1

The why?