From 39f8b6cf162feafe42cd8e608bd8c11d706d7004 Mon Sep 17 00:00:00 2001
From: Phil Wang <lucidrains@gmail.com>
Date: Mon, 19 Sep 2022 10:45:20 -0700
Subject: [PATCH] show example of using SOTA open sourced open clip

---
 README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 061e304..79f6fe3 100644
--- a/README.md
+++ b/README.md
@@ -634,10 +634,12 @@ Alternatively, you can also use <a href="https://github.com/mlfoundations/open_c
 $ pip install open-clip-torch
 ```
 
+Ex. using the <a href="https://laion.ai/blog/large-openclip/">SOTA Open Clip</a> model trained by <a href="https://github.com/rom1504">Romain</a>
+
 ```python
 from dalle2_pytorch import OpenClipAdapter
 
-clip = OpenClipAdapter()
+clip = OpenClipAdapter('ViT-H/14')
 ```
 
 Now you'll just have to worry about training the Prior and the Decoder!