From 2cac0472ad0d957c74be6e28fa1541c39981c310 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Thu, 29 Sep 2022 16:10:08 +0300
Subject: [PATCH] Updated Negative prompt (markdown)

---
 Negative-prompt.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Negative-prompt.md b/Negative-prompt.md
index 534adf0..13cc6f1 100644
--- a/Negative-prompt.md
+++ b/Negative-prompt.md
@@ -2,7 +2,7 @@ Negative prompt is a way to use the Stable Diffusion in a way that allows the us
 
 The way negative prompt works is by using user-specified text instead of empty string for `unconditional_conditioning` when doing sampling.
 
-Here's (simplified) code from [txt2img.py](https://github.com/CompVis/stable-diffusion/blob/main/scripts/txt2img.py):
+Here's the (simplified) code from [txt2img.py](https://github.com/CompVis/stable-diffusion/blob/main/scripts/txt2img.py):
 
 ```python
 # prompts = ["a castle in a forest"]
@@ -14,7 +14,7 @@ uc = model.get_learned_conditioning(batch_size * [""])
 samples_ddim, _ = sampler.sample(conditioning=c, unconditional_conditioning=uc, [...])
 ```
 
-This launches sampler that repeatedly:
+This launches the sampler that repeatedly:
 - de-noises the picture guiding it to look more like your prompt (conditioning)
 - de-noises the picture guiding it to look more like an empty prompt (unconditional_conditioning)
 - looks at difference between those and uses it to produce a set of changes for the noisy picture (different samplers do that part differently)