From c0ea13f94eed4716a3b710649852170c23e39f85 Mon Sep 17 00:00:00 2001
From: ExponentialML <59846140+ExponentialML@users.noreply.github.com>
Date: Fri, 8 Mar 2024 12:40:07 -0800
Subject: [PATCH] Update README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 8d4de8f..2cac550 100644
--- a/README.md
+++ b/README.md
@@ -48,9 +48,9 @@ This is optional if you're not using the attention layers, and are using somethi
 ### Tips
 
 1. If you're using pure ModelScope, try higher CFG (around 15) for better coherence. You may also try any other rescale nodes.
-2. If using pure ModelScope, ensure that you use a minimum of 24 frames.
+2. When using pure ModelScope, ensure that you use a minimum of 24 frames.
 3. If using with AnimateDiff, make sure to use 16 frames if you're not using context options.
-
+4. You **must** use the same CLIP model as the 1.5 checkpoint if you have `enable_attn` disabled.
 
 ## TODO