Three things that broke when I moved AI image models into the browser

Automated excerpt

I rebuilt a retired photo-editing site so that every model runs client-side: object removal (MI-GAN, LaMa), background removal (RMBG-1. 4) and 4× upscaling (Real-ESRGAN), all through ONNX Runtime Web with WebGPU and a WebAssembly fallback. A model can be silently wrong on WebGPU LaMa ran on WebGPU without any error. Tool pages load no model, no runtime, not even the worker.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.