NanoDiffuser: sub-400 MiB text-to-image model running in-browser via WebGPU
jason_mayes · x · 2026-09-06
NanoDiffuser is a text-to-image generator under 400 MiB that runs entirely locally in the browser via WebGPU, producing images in under 3 seconds on mid-tier laptops and under 6 seconds on mid-tier phones. It's a heavily modified Stable Diffusion, and the author built the conversion pipeline and compatibility patches enabling browser inference; full technical details are on the model page.
More from Infra
- Hands-on test: AI ops agent Ghost diagnoses and fixes three simultaneous service failures — BLUECOW009 · 2026-09-07
- Andy Masley accuses Benn Jordan of dodging fact-checks on viral data center infrasound video — AndyMasley · 2026-09-07
- Guide: Run DLSS 5 Real-Time Video Playback on RTX 20/30 Series via MPV — Miserable-Option5488 · 2026-09-07
- Your memory layer may be silently breaking prompt cache on every request, at up to 12.5x cost — inbask · 2026-09-07
- OpenRouter crosses 400T monthly inference tokens, up ~27x in a year — gajesh · 2026-09-07
- Goldman Sachs sees nearly 80% upside for Kospi at 12,000 target on AI memory boom — Polymarket · 2026-09-07