Update app.py

fixed interactive

app.py

@@ -16,7 +16,7 @@ def inference(raw_image):
     caption = processor.decode(out[0], skip_special_tokens=True)
     return caption
 
-inputs = gr.Image(type="pil", interactive=False)
+inputs = gr.Image(type="pil", interactive=True)
 outputs = gr.Textbox(label="Caption")
 
 description = "Gradio demo for FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions. This demo features a BLIP-based model, trained using FuseCap."