Projects

Developing tools for building image and captioning datasets, training computer vision models, and building analysis tools.

Working on

• Building parameter efficient model analysis tools in Rust and WASM with Flux, SDXL, and PEFT support
• Building image captioning and VLM fine-tuning using LoRA and other parameter efficient methods
• Enhancing training systems for diffusion models with ongoing development and open PRs
• Building wavelet-based loss calculations for training diffusion and image models
• Building algo based image tools like pixel sorting and dithering with ComfyUI nodes
• Contributing to open source projects in Neovim, LLM tooling, and Rust