From 47feed88770cd738273bde5c43148357fe36bba1 Mon Sep 17 00:00:00 2001 From: ydobemos Date: Wed, 2 Nov 2022 18:51:07 +0200 Subject: [PATCH] Update README.md --- README.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 24b4068..75dfdae 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ ![Logo](https://user-images.githubusercontent.com/17021558/197962979-43290ce2-9a62-49c7-8295-5ad3fcdd1df0.png) ## Introduction -**StylePile** is a script for https://github.com/AUTOMATIC1111/stable-diffusion-webui to mix and match elements to prompts that affect the style of the result. Hence the name. By default, these elements are placed in a specific order and given strength values. Which means the result sort-of evolves. I have generated thousands of images for each main **Image type** and tweaked the keywords to attempt giving expected results most of the time. Here are some examples on what you can get with a couple of clicks: +**StylePile**[^1] is a script for https://github.com/AUTOMATIC1111/stable-diffusion-webui to mix and match elements to prompts that affect the style of the result. Hence the name. By default, these elements are placed in a specific order and given strength values. Which means the result sort-of evolves. I have generated thousands of images for each main **Image type** and tweaked the keywords to attempt giving expected results most of the time. Here are some examples on what you can get with a couple of clicks: ![F](https://user-images.githubusercontent.com/17021558/199468444-99e78027-1889-4bec-b97b-25f801e33c0a.jpg) ![A](https://user-images.githubusercontent.com/17021558/199458710-efc7520d-70a1-475b-8ca0-dbdc3182b865.jpg) @@ -42,11 +42,10 @@ Additionally the command line will also share more information than by default s ![image](https://user-images.githubusercontent.com/17021558/199454650-c0859776-0bbb-4ad1-b037-6ad4b4b75cd3.png) ## In conclusion -I made this because manually changing keywords, looking up possible styles, etc was a pain. It is meant as a fun tool to explore possibilities and make learning Stable Diffusion easier. If you have some ideas or, better yet, would like to contribute* in some way do get in touch. -*Hey, if you have a 12Gb graphics card just laying around I'm happy to take it (: +I made this because manually changing keywords, looking up possible styles, etc was a pain. It is meant as a fun tool to explore possibilities and make learning Stable Diffusion easier. If you have some ideas or, better yet, would like to contribute[^2] in some way do get in touch. ## Installation -Click the green **Code** button at the top of the page, select the **Download ZIP** option. When done extract the **StylePile.py** file from there and drop it into your **stable-diffusion-webui/scripts** folder. Upon next launch it should be available at the bottom **Script** dropdown. +Click the green **Code** button at the top of the page, select the **Download ZIP** option. When done extract everything from there and drop it into your **stable-diffusion-webui/scripts** folder. Upon next launch it should be available at the bottom **Script** dropdown. Loading the scripts may take a little while, so it won't appear right away. @@ -79,3 +78,6 @@ So you should just mix and match and experiment to find out which styles work we For example, you liked that lady knight example from above, but would prefer it as a painting. Just transfer it to img2img, mix styles with Focus and get a pleasant result quickly (but, preferrably do a batch, Stable Diffusion still doesn't magically make every result great). ![2022-10-21 09 56 57 127 0 0 1 8469e9f6d637](https://user-images.githubusercontent.com/17021558/197132497-f5d6b9cb-7ac1-4c83-94ba-4b0b13fc90ef.png) + +[^1]: Pun intended. +[^2]: Hey, if you have a 12Gb graphics card just laying around I'm happy to take it (: