Update app.py

app.py

@@ -9,16 +9,13 @@ model = BlipForConditionalGeneration.from_pretrained(model_id)
 processor = BlipProcessor.from_pretrained(model_id)
 
 def launch(input_image):
-    # Convert Gradio image input to PIL Image
-    image = Image.fromarray(input_image)
-
-    # Process the image and generate a caption
+    image = input_image.convert('RGB')
     inputs = processor(image, return_tensors="pt")
     out = model.generate(**inputs)
     caption = processor.decode(out[0], skip_special_tokens=True)
-
     return caption
 
+
 iface = gr.Interface(
     launch, 
     inputs=gr.inputs.Image(type="pil"),  # Set input type to image