From 288d1aa9038c1fcbecc2141fdf43c1eed154c8ba Mon Sep 17 00:00:00 2001 From: cmdr2 Date: Thu, 31 Aug 2023 16:42:36 +0530 Subject: [PATCH] Updated SDXL (markdown) --- SDXL.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/SDXL.md b/SDXL.md index a8821e0..dd56a79 100644 --- a/SDXL.md +++ b/SDXL.md @@ -1,4 +1,6 @@ -SDXL can create larger images with better image quality. +SDXL models are trained to create larger images with better image quality. But they can consume more GPU and system RAM, as compared to the Stable Diffusion version 1 or 2 models. + +SDXL models can also make good images at 512x512 resolution, so they're often a good replacement for SD 1 or 2 models, in terms of image quality. Steps: 1. Download whichever SDXL model you want: @@ -6,6 +8,8 @@ Steps: * Refiner model (image-to-image only): https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/resolve/main/sd_xl_refiner_1.0.safetensors 2. Save the model to the `models/stable-diffusion` folder. +![image](https://github.com/easydiffusion/easydiffusion/assets/844287/7425c9e7-c35a-489e-bcf5-c80ca83dd175) + Finally, in the Easy Diffusion UI, click the "refresh" icon next to the Models dropdown, and select the downloaded model and generate the image. # Usage tips: