Update app.py

app.py

@@ -20,8 +20,8 @@ vision_model = MllamaForConditionalGeneration.from_pretrained(
 )
 processor = AutoProcessor.from_pretrained(llama_vision_model_id, token=hf_token)
 
-# Set up segmentation model using Segment Anything 2 from Hugging Face Hub
-segment_model_id = "camenduru/segment-anything-2"
+# Set up segmentation model using MaskFormer Swin Large from Hugging Face Hub
+segment_model_id = "facebook/maskformer-swin-large"
 segment_pipe = pipeline(
     "image-segmentation",
     model=segment_model_id,
@@ -45,7 +45,7 @@ def process_image(image):
     output = vision_model.generate(**inputs, max_new_tokens=50)
     caption = processor.decode(output[0], skip_special_tokens=True)
 
-    # Step 2: Segment important parts of the image using Segment Anything 2
+    # Step 2: Segment important parts of the image using MaskFormer Swin Large
     segmented_result = segment_pipe(image=image)
     segments = segmented_result