diff --git a/README.md b/README.md
index be5ee8c..bdacb35 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # docker-ffmpeg-gpu
 
-Use `ffmpeg` with `docker` and `nvidia` powers to transcode in Debian 11 Bullseye, based on [this nice docker project](https://git.archive.org/www/ffmpeg-gpu)
+Use `ffmpeg` with `docker` and `nvidia` powers to transcode in Debian GNU/Linux, based on [this nice docker project](https://git.archive.org/www/ffmpeg-gpu)
 
                  (__) 
                  (oo) 
@@ -22,13 +22,13 @@ Use `ffmpeg` with `docker` and `nvidia` powers to transcode in Debian 11 Bullsey
 ## Pull docker image
 
 	$ docker pull registry.manalejandro.com/docker-ffmpeg-gpu
+	$ docker tag registry.manalejandro.com/docker-ffmpeg-gpu docker-ffmpeg-gpu
 
 ## Usage
 
 ### You can use "/ffmpeg" or "/ffmpeg-pascal" for architecture version
 
-	$ docker-compose up -d
-	$ docker-compose run --rm --entrypoint /ffmpeg nvidia-ffmpeg -hwaccels -v 0
+	$ docker-compose run --rm docker-ffmpeg-gpu -hwaccels -v 0
 
 	Hardware acceleration methods:
 	vdpau
@@ -37,15 +37,11 @@ Use `ffmpeg` with `docker` and `nvidia` powers to transcode in Debian 11 Bullsey
 	
 ## Sample using CUDA for encoding:
 
-	$ docker-compose run --rm --entrypoint /ffmpeg nvidia-ffmpeg -vsync 0 -i /folder/input -c:a copy -c:v h264_nvenc /folder/output
+	$ docker-compose run --rm --entrypoint /ffmpeg docker-ffmpeg-gpu -vsync 0 -i /folder/input -c:a copy -c:v h264_nvenc /folder/output
 
 ## Full hardware transcode with NVDEC and NVENC:
 
-	$ docker-compose run --rm --entrypoint /ffmpeg nvidia-ffmpeg -vsync 0 -hwaccel nvdec -hwaccel_output_format cuda -extra_hw_frames 10 -i /folder/input -c:a copy -c:v h264_nvenc /folder/output
-
-## Shutdown
-
-	$ docker-compose down
+	$ docker-compose run --rm --entrypoint /ffmpeg-pascal docker-ffmpeg-gpu -vsync 0 -hwaccel nvdec -hwaccel_output_format cuda -extra_hw_frames 10 -i /folder/input -c:a copy -c:v h264_nvenc /folder/output
 
 ## License