What’s the bottleneck, rembg, Pillow, or OpenAI?

OpenAI by a country mile, and only when it’s in the loop. rembg is ~2-4 sec on CPU (sub-second on GPU). Pillow ops are ~200ms. OpenAI gpt-image-1 is 8-15 sec per generated angle plus rate-limit waits. If you fire 3 angles per SKU, you’re looking at 30-50 sec per SKU end-to-end vs ~3 sec for the self-host-only path. For high-volume real-time use, the pattern is: process and publish the cleaned hero immediately (3 sec, instant PDP improvement); enqueue the AI angle-gen as a low-priority follow-up that completes minutes later. Don’t let the OpenAI step block the “PDP looks better” visible win.