diff --git a/README.md b/README.md
index 51e6e104e80857594b9ef871732c898562d1180b..d43bdb087b9d38513e5a380400dbdb27853d9352 100644
--- a/README.md
+++ b/README.md
@@ -42,9 +42,9 @@ Your goal is to train a model that can complete a lap as fast as possible withou
 
 In this challenge, you will train your models locally and then upload them to AIcrowd (via git) to be evaluated.
 
-<!-- **The following is a high level description of how this process works.** -->
+**The following is a high level description of how this process works.**
 
-<!-- <div class="tenor-gif-embed" data-postid="22946542" data-share-method="host" data-width="100%" data-aspect-ratio="5.03030303030303"><a href="https://tenor.com/view/gif-22946542">GIF</a> </div><script type="text/javascript" async src="https://tenor.com/embed.js"></script> -->
+![Submission Flow](https://gitlab.aicrowd.com/deepracer/neurips-2021-aws-deepracer-starter-kit/-/raw/master/docs/submission_flow.gif)
 
 1. **Sign up** to join the competition [on the AIcrowd website](https://www.aicrowd.com/challenges/neurips-2021-aws-deepracer-ai-driving-olympics-challenge).
 2. **Clone** this repo and start developing your solution.
diff --git a/deepracer-gym/start_deepracer_docker.sh b/deepracer-gym/start_deepracer_docker.sh
index 796272f58e5ad6a06bb7d55d78110b090e0faa1d..cb042782a383d259afb0d63f0fbd0799021767f6 100644
--- a/deepracer-gym/start_deepracer_docker.sh
+++ b/deepracer-gym/start_deepracer_docker.sh
@@ -1 +1 @@
-docker run -it --rm --name=deepracer -p 8888:8888 -p 5000:5000 --cpus="3" --memory="6g" aicrowd/deepracer:round1_release /bin/bash
\ No newline at end of file
+docker run -it --rm --name=deepracer -p 8888:8888 -p 5000:5000 --cpus="3" --memory="6g" aicrowd/base-images:deepracer_round1_release /bin/bash
diff --git a/docs/submission_flow.gif b/docs/submission_flow.gif
new file mode 100644
index 0000000000000000000000000000000000000000..03598262769e6e202782aac5d2aea4e08fad23a8
Binary files /dev/null and b/docs/submission_flow.gif differ