From 3f65aa10a228c78ac2925905527639d49658d970 Mon Sep 17 00:00:00 2001 From: techjarves Date: Thu, 4 Jun 2026 21:21:57 +0530 Subject: [PATCH] docs: add performance benchmarks table to README --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index 300cd9a..c5a0255 100644 --- a/README.md +++ b/README.md @@ -64,6 +64,16 @@ local-ai-image-generator/ --- +## ⏱️ Performance Benchmarks + +Typical generation times for an image with **20 steps** (e.g. 512x512 resolution): + +* **CUDA GPU (Nvidia):** ~10 seconds. +* **Vulkan GPU (AMD / Intel Arc / GTX fallback):** ~89 seconds. +* **CPU (Fallback):** ~150 - 300+ seconds (highly dependent on processor core count, speed, and AVX instruction sets). + +--- + ## 🛠️ Troubleshooting * **Reset Environment:** If a build fails or you want to clear dependencies, run `scripts/reset.ps1`. (This preserves your models and generated images). * **Port Conflicts:** The application binds to ports `1420` (Frontend) and `8080` (Backend API). Ensure these are free.