Where the 150 seconds actually go: profiling a local render loop

I generate on a 4GB GTX 1650, SD1.5 in fp32 with model offload. One 512x768 image takes about 150 seconds. That number is useless on its own — it tells me nothing about what to change. So I timed the loop in pieces. Splitting the 150 seconds into model load, sampling steps, and PNG encode The first…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

1. 2026-11-03 13:33 · DEV Community — AI
   Where the 150 seconds actually go: profiling a local render loop