Use JSON output

app.py

@@ -40,17 +40,17 @@ def generate(image):
     inputs = inputs.to("cuda")
 
     # Inference: Generation of the output
-    generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids = model.generate(**inputs, max_new_tokens=300)
     generated_ids_trimmed = [
         out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
     ]
     output_text = processor.batch_decode(
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
     )
-    return output_text
+    return output_text[0]
 
 inputs = gr.Image(type="pil", label="Input Image")
-outputs = gr.Textbox(label="Output")
+outputs = gr.JSON(label="Output")
 
 demo = gr.Interface(fn=generate, inputs=inputs, outputs=outputs, deep_link=False)
 demo.launch()