docs: load image processor via from_weights

README.md

@@ -43,7 +43,7 @@ from PIL import Image
 from kerasformers.models.mask2former import Mask2FormerUniversalSegment, Mask2FormerImageProcessor
 
 model = Mask2FormerUniversalSegment.from_weights("kerasformers/mask2former-swin-tiny-coco-instance")
-processor = Mask2FormerImageProcessor()
+processor = Mask2FormerImageProcessor.from_weights("kerasformers/mask2former-swin-tiny-coco-instance")
 
 image = Image.open("your_image.jpg").convert("RGB")
 output = model(processor(image)["pixel_values"], training=False)