Update app.py

app.py

@@ -10,9 +10,9 @@ dmodel = DetrForObjectDetection.from_pretrained('facebook/detr-resnet-50')
 model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
-i1 = gr.inputs.Image()
+i1 = gr.inputs.Image(type="pil")
 i2 = gr.inputs.Textbox()
-o1 = gr.outputs.Image()
+o1 = gr.outputs.Image(type="pil")
 o2 = gr.outputs.Textbox()
 
 def extract_image(image, text, num=1):