Update app.py

app.py

@@ -291,12 +291,12 @@ class BLIPVQA:
 class ConversationBot:
     def __init__(self):
         print("Initializing VisualChatGPT")
-        self.edit = ImageEditing(device="cuda:0")
+        #self.edit = ImageEditing(device="cuda:0")
         self.i2t = ImageCaptioning(device="cuda:0")
         self.t2i = T2I(device="cuda:0")
         self.image2canny = image2canny()
         #self.canny2image = canny2image(device="cuda:0")
-        #self.BLIPVQA = BLIPVQA(device="cuda:0")
+        self.BLIPVQA = BLIPVQA(device="cuda:0")
         #self.pix2pix = Pix2Pix(device="cuda:0")
         self.memory = ConversationBufferMemory(memory_key="chat_history", output_key='output')
         self.tools = [
@@ -306,19 +306,19 @@ class ConversationBot:
             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. "),
-            Tool(name="Remove Something From The Photo", func=self.edit.remove_part_of_image,
-                 description="useful when you want to remove and object or something from the photo from its description or location. "
-                             "The input to this tool should be a comma seperated string of two, representing the image_path and the object need to be removed. "),
-            Tool(name="Replace Something From The Photo", func=self.edit.replace_part_of_image,
-                 description="useful when you want to replace an object from the object description or location with another object from its description. "
-                             "The input to this tool should be a comma seperated string of three, representing the image_path, the object to be replaced, the object to be replaced with "),
+            #Tool(name="Remove Something From The Photo", func=self.edit.remove_part_of_image,
+            #     description="useful when you want to remove and object or something from the photo from its description or location. "
+             #                "The input to this tool should be a comma seperated string of two, representing the image_path and the object need to be removed. "),
+            #Tool(name="Replace Something From The Photo", func=self.edit.replace_part_of_image,
+                 #description="useful when you want to replace an object from the object description or location with another object from its description. "
+                             #"The input to this tool should be a comma seperated string of three, representing the image_path, the object to be replaced, the object to be replaced with "),
 
             #Tool(name="Instruct Image Using Text", func=self.pix2pix.inference,
             #     description="useful when you want to the style of the image to be like the text. like: make it look like a painting. or make it like a robot. "
             #                 "The input to this tool should be a comma seperated string of two, representing the image_path and the text. "),
-            #Tool(name="Answer Question About The Image", func=self.BLIPVQA.get_answer_from_question_and_image,
-            #     description="useful when you need an answer for a question based on an image. like: what is the background color of the last image, how many cats in this figure, what is in this figure. "
-            #                 "The input to this tool should be a comma seperated string of two, representing the image_path and the question"),
+            Tool(name="Answer Question About The Image", func=self.BLIPVQA.get_answer_from_question_and_image,
+                 description="useful when you need an answer for a question based on an image. like: what is the background color of the last image, how many cats in this figure, what is in this figure. "
+                             "The input to this tool should be a comma seperated string of two, representing the image_path and the question"),
             Tool(name="Edge Detection On Image", func=self.image2canny.inference,
                  description="useful when you want to detect the edge of the image. like: detect the edges of this image, or canny detection on image, or peform edge detection on this image, or detect the canny image of this image. "
                              "The input to this tool should be a string, representing the image_path"),
@@ -420,9 +420,8 @@ class ConversationBot:
 
 bot = ConversationBot()
 with gr.Blocks(css="#chatbot .overflow-y-auto{height:500px}") as demo:
+    gr.Markdown("# Visual ChatGPT  <p> Currently supports text, image captioning, image generation, and visual quesetion answering</p>'")
     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([])