diff --git a/README.md b/README.md
index 7314731..39fe0ac 100644
--- a/README.md
+++ b/README.md
@@ -15,11 +15,17 @@ Full license text in LICENSE file
 
 ## Notes on cloning:
 
-- This repo has about 7.5GB of datasets in it. The download will take a while.
 - `pypho` is added as a submodule -> `--recurse-submodules`
+- This repo has about 7.5GB of datasets in it. The `git lfs fetch` step will take a while.
 
 ```bash
-git clone --recurse-submodules https://git.suuppl.dev/seppl/optical-regeneration.git
+apt install git-lfs
+# only necessary once per user account
+git lfs install
+
+git clone --recurse-submodules https://git.suuppl.dev/seppl/optical-regeneration.git && cd optical-regeneration
+git lfs fetch
+git lfs checkout
 ```
 
 ## License