From b33c331f0c665268ce6921bb8e2900e6a875900f Mon Sep 17 00:00:00 2001
From: Olivv <133010426+olivv-cs@users.noreply.github.com>
Date: Wed, 11 Jun 2025 11:32:53 +0300
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f6c17300..40da9b55 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ Inputs:
                 ]
                 return tokenizer.apply_chat_template(messages, add_generation_prompt=False, return_tensors="pt").to("cuda")
 
-Technically speaking, it's possible to load just any model as instruct one. It might not even be an instruct model.
+Technically speaking, it's possible to load just any model as text encoder.
 
 Outputs:
 Just CLIP. Pass it through your nodes like you will do with regular DualCLIPLoader.