Fix potential issue with batch size and clip vision.

comfy/clip_vision.py

@@ -25,6 +25,8 @@ class ClipVisionModel():
 
     def encode_image(self, image):
         img = torch.clip((255. * image), 0, 255).round().int()
+        if len(img.shape) == 3:
+            img = [img]
         inputs = self.processor(images=img, return_tensors="pt")
         outputs = self.model(**inputs)
         return outputs