From 1dba74dd174e49435bc959c13e118d60396a630b Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Fri, 21 Oct 2022 09:19:07 +0300
Subject: [PATCH] Updated Features (markdown)

---
 Features.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Features.md b/Features.md
index 39ac70e..c02261d 100644
--- a/Features.md
+++ b/Features.md
@@ -34,6 +34,15 @@ Options for inpainting:
 - erase a part of the picture in an external editor and upload a transparent picture. Any even slightly transparent areas will become part of the mask. Be aware that [some editors](https://docs.krita.org/en/reference_manual/layers_and_masks/split_alpha.html#how-to-save-a-png-texture-and-keep-color-values-in-fully-transparent-areas) save completely transparent areas as black by default.
 - change mode (to the bottom right of the picture) to "Upload mask" and choose a separate black and white image for the mask (white=inpaint).
 
+## Inpainting model
+RunwayML has trained an additional model specifically designed for inpainting. This model accepts additional inputs - the initial image without noise plus the mask - and seems to be much better at the job.
+
+Download and extra info for the model is here: https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion
+
+To use the model, you must rename the checkpoint so that its filename ends in `inpainting.ckpt`, for example, `1.5-inpainting.ckpt`.
+
+After that just select the checkpoint as you'd usually select any checkpoint and you're good to go.
+
 ## Masked content
 The masked content field determines content is placed to put into the masked regions before they are inpainted.