From 31914c9beb5d1b2d0e4062d1fa6a6304458ec9d9 Mon Sep 17 00:00:00 2001
From: hben35096 <139383150+hben35096@users.noreply.github.com>
Date: Sat, 10 May 2025 13:47:35 +0800
Subject: [PATCH] Use the CPU for interpolation.

---
 comfy/clip_vision.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/comfy/clip_vision.py b/comfy/clip_vision.py
index 8f592652e..92cd6b179 100644
--- a/comfy/clip_vision.py
+++ b/comfy/clip_vision.py
@@ -29,7 +29,12 @@ def clip_preprocess(image, size=224, mean=[0.48145466, 0.4578275, 0.40821073], s
         else:
             scale_size = (size, size)
 
-        image = torch.nn.functional.interpolate(image, size=scale_size, mode="bilinear")
+        if image.device.type == 'musa':
+            image = image.cpu()
+            image = torch.nn.functional.interpolate(image, size=scale_size, mode="bicubic", antialias=True)
+            image = image.to('musa')
+        else:
+            image = torch.nn.functional.interpolate(image, size=scale_size, mode="bicubic", antialias=True)
         h = (image.shape[2] - size)//2
         w = (image.shape[3] - size)//2
         image = image[:,:,h:h+size,w:w+size]