From 9961970e4ef4c1726156c1df557bb5a922eccf33 Mon Sep 17 00:00:00 2001
From: Olivv <133010426+olivv-cs@users.noreply.github.com>
Date: Fri, 13 Jun 2025 22:02:04 +0300
Subject: [PATCH] mistake in description fix

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

diff --git a/README.md b/README.md
index c303d3e3..a3ff585d 100644
--- a/README.md
+++ b/README.md
@@ -22,7 +22,7 @@ Also if you have 24GB of VRAM or less, you might go OOM in Comfy - that's expect
 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.
+Just text. Pass it to any node that accepts text as input.
 
 **FunPack img2latent Interpolation**