Update app.py

app.py

@@ -43,8 +43,6 @@ def run_example(task_prompt, image, text_input=None, model_id='microsoft/Florenc
         prompt = task_prompt
     else:
         prompt = task_prompt + text_input
-    iimage=image
-    image=fig_to_pil(image)
     inputs = processor(text=prompt, images=image, return_tensors="pt").to("cuda")
     generated_ids = model.generate(
         input_ids=inputs["input_ids"],
@@ -118,7 +116,7 @@ def draw_ocr_bboxes(image, prediction):
     return image
 
 def process_image(image, task_prompt, text_input=None, model_id='microsoft/Florence-2-large'):
-    image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+    image = Image.open(image)  # Convert NumPy array to PIL Image
     if task_prompt == 'Caption':
         task_prompt = '<CAPTION>'
         results = run_example(task_prompt, image, model_id=model_id)
@@ -193,13 +191,14 @@ def process_image(image, task_prompt, text_input=None, model_id='microsoft/Flore
 
 
 gradio_app_bill= gr.Interface(
-    fn=run_example,
+    fn=process_image,
     inputs=[
+        gr.Image(type='filepath'),
         gr.Dropdown(choices=[
         'Caption', 'Detailed Caption', 'More Detailed Caption',
         'OCR', 'OCR with Region'
         ], label="Task Prompt", value= 'More Detailed Caption'),
-        gr.Image(type='filepath'),
+        
         gr.Textbox(label="Text Input (optional)"),
         gr.Dropdown(choices=list(models.keys()), label="Model", value='microsoft/Florence-2-large')
     ],