From 1ba4b578a0a81c718dd94c252440b5f2ca7d1d57 Mon Sep 17 00:00:00 2001
From: Johannes Stelzer <jsdmail@gmail.com>
Date: Tue, 9 Jan 2024 21:11:40 +0100
Subject: [PATCH] Update README.md

---
 README.md | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 2806407..0f0ce40 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,6 @@
 
 Latent blending enables video transitions with incredible smoothness between prompts, computed within seconds. Powered by [stable diffusion XL](https://stability.ai/stable-diffusion), this method involves specific mixing of intermediate latent representations to create a seamless transition – with users having the option to fully customize the transition directly in high-resolution. The new version also supports SDXL Turbo, allowing to generate transitions faster than they are typically played back!
 
-
 ```python
 pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16").to("cuda")
 dh = DiffusersHolder(pipe)
@@ -18,6 +17,13 @@ lb.run_transition()
 lb.write_movie_transition('movie_example1.mp4', duration_transition=12)
 
 ```
+
+# Installation
+```commandline
+pip install git+https://github.com/lunarring/latentblending
+```
+
+
 ## Gradio UI
 Coming soon again :)
 
@@ -90,12 +96,6 @@ lb.set_parental_crossfeed(crossfeed_power, crossfeed_range, crossfeed_decay)
 ```
 
 
-# Installation
-#### Packages
-```commandline
-pip install -r requirements.txt
-```
-
 # How does latent blending work?
 ## Method
 ![](animation.gif)