Update app.py

app.py

@@ -292,7 +292,7 @@ class ConversationBot:
     def __init__(self):
         print("Initializing VisualChatGPT")
         #self.edit = ImageEditing(device="cuda:0")
-        #self.i2t = ImageCaptioning(device="cuda:0")
+        self.i2t = ImageCaptioning(device="cuda:0")
         self.t2i = T2I(device="cuda:0")
         self.image2canny = image2canny()
         #self.canny2image = canny2image(device="cuda:0")
@@ -300,9 +300,9 @@ class ConversationBot:
         #self.pix2pix = Pix2Pix(device="cuda:0")
         self.memory = ConversationBufferMemory(memory_key="chat_history", output_key='output')
         self.tools = [
-            #Tool(name="Get Photo Description", func=self.i2t.inference,
-            #     description="useful when you want to know what is inside the photo. receives image_path as input. "
-            #                 "The input to this tool should be a string, representing the image_path. "),
+            Tool(name="Get Photo Description", func=self.i2t.inference,
+                 description="useful when you want to know what is inside the photo. receives image_path as input. "
+                             "The input to this tool should be a string, representing the image_path. "),
             Tool(name="Generate Image From User Input Text", func=self.t2i.inference,
                  description="useful when you want to generate an image from a user input text and save it to a file. like: generate an image of an object or something, or generate an image that includes some objects. "
                              "The input to this tool should be a string, representing the text used to generate image. "),
@@ -422,18 +422,17 @@ bot = ConversationBot()
 with gr.Blocks(css="#chatbot .overflow-y-auto{height:500px}") as demo:
     openai_api_key_input = gr.Textbox(type = "password", label = "Enter your OpenAI API key here")    
     
+
+    chatbot = gr.Chatbot(elem_id="chatbot", label="Visual ChatGPT")
+    state = gr.State([])
+
     with gr.Row(visible = False) as input_row:
-        with gr.Row():
-            chatbot = gr.Chatbot(elem_id="chatbot", label="Visual ChatGPT")
-            state = gr.State([])
-
-        with gr.Row():
-            with gr.Column(scale=0.7):
-                txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter, or upload an image").style(container=False)
-            with gr.Column(scale=0.15, min_width=0):
-                clear = gr.Button("Clear️")
-            with gr.Column(scale=0.15, min_width=0):
-                btn = gr.UploadButton("Upload", file_types=["image"])
+        with gr.Column(scale=0.7):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter, or upload an image").style(container=False)
+        with gr.Column(scale=0.15, min_width=0):
+            clear = gr.Button("Clear️")
+        with gr.Column(scale=0.15, min_width=0):
+            btn = gr.UploadButton("Upload", file_types=["image"])
 
     openai_api_key_input.submit(bot.init_langchain,openai_api_key_input,[input_row])
     txt.submit(bot.run_text, [txt, state], [chatbot, state])