api key

app.py

@@ -67,149 +67,77 @@ def cut_dialogue_history(history_memory, keep_last_n_words=400):
 
 
 class ConversationBot:
-    def __init__(self):
-        print("Initializing VisualChatGPT")
-        self.edit = ImageEditing(device="cuda:0")
-        self.i2t = ImageCaptioning(device="cuda:0")
-        self.t2i = T2I(device="cuda:0")
-        self.BLIPVQA = BLIPVQA(device="cuda:0")
-        self.pix2pix = Pix2Pix(device="cuda:0")
-        self.image2canny = image2canny()
-        self.canny2image = canny2image(device="cuda:0")
-        # self.image2line = image2line()
-        # self.line2image = line2image(device="cuda:0")
-        # self.image2hed = image2hed()
-        # self.hed2image = hed2image(device="cuda:0")
-        # self.image2scribble = image2scribble()
-        # self.scribble2image = scribble2image(device="cuda:0")
-        # self.image2pose = image2pose()
-        # self.pose2image = pose2image(device="cuda:0")
-        # self.image2seg = image2seg_new()
-        # self.seg2image = seg2image_new(device="cuda:0")
-        # self.image2depth = image2depth_new()
-        # self.depth2image = depth2image_new(device="cuda:0")
-        # self.image2normal = image2normal_new()
-        # self.normal2image = normal2image_new(device="cuda:0")
+    def __init__(self, load_dict):
+        # load_dict = {'VisualQuestionAnswering':'cuda:0', 'ImageCaptioning':'cuda:1',...}
+        print(f"Initializing VisualChatGPT, load_dict={load_dict}")
+        if 'ImageCaptioning' not in load_dict:
+            raise ValueError("You have to load ImageCaptioning as a basic function for VisualChatGPT")
+
         self.memory = ConversationBufferMemory(memory_key="chat_history", output_key='output')
-        self.tools = [
-            Tool(name="Get Photo Description", func=self.i2t.inference,
-                 description="useful for 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 for when you want to generate an image from a user input text and it saved 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 for 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 for 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 for 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 for 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 for 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"),
-            Tool(name="Generate Image Condition On Canny Image", func=self.canny2image.inference,
-                 description="useful for when you want to generate a new real image from both the user desciption and a canny image. like: generate a real image of a object or something from this canny image, or generate a new real image of a object or something from this edge image. "
-                             "The input to this tool should be a comma seperated string of two, representing the image_path and the user description. "),
-            # Tool(name="Line Detection On Image", func=self.image2line.inference,
-            #      description="useful for when you want to detect the straight line of the image. like: detect the straight lines of this image, or straight line detection on image, or peform straight line detection on this image, or detect the straight line image of this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Line Image", func=self.line2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and a straight line image. like: generate a real image of a object or something from this straight line image, or generate a new real image of a object or something from this straight lines. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description. "),
-            # Tool(name="Hed Detection On Image", func=self.image2hed.inference,
-            #      description="useful for when you want to detect the soft hed boundary of the image. like: detect the soft hed boundary of this image, or hed boundary detection on image, or peform hed boundary detection on this image, or detect soft hed boundary image of this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Soft Hed Boundary Image", func=self.hed2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and a soft hed boundary image. like: generate a real image of a object or something from this soft hed boundary image, or generate a new real image of a object or something from this hed boundary. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description"),
-            # Tool(name="Segmentation On Image", func=self.image2seg.inference,
-            #      description="useful for when you want to detect segmentations of the image. like: segment this image, or generate segmentations on this image, or peform segmentation on this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Segmentations", func=self.seg2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and segmentations. like: generate a real image of a object or something from this segmentation image, or generate a new real image of a object or something from these segmentations. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description"),
-            # Tool(name="Predict Depth On Image", func=self.image2depth.inference,
-            #      description="useful for when you want to detect depth of the image. like: generate the depth from this image, or detect the depth map on this image, or predict the depth for this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Depth",  func=self.depth2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and depth image. like: generate a real image of a object or something from this depth image, or generate a new real image of a object or something from the depth map. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description"),
-            # Tool(name="Predict Normal Map On Image", func=self.image2normal.inference,
-            #      description="useful for when you want to detect norm map of the image. like: generate normal map from this image, or predict normal map of this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Normal Map", func=self.normal2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and normal map. like: generate a real image of a object or something from this normal map, or generate a new real image of a object or something from the normal map. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description"),
-            # Tool(name="Sketch Detection On Image", func=self.image2scribble.inference,
-            #      description="useful for when you want to generate a scribble of the image. like: generate a scribble of this image, or generate a sketch from this image, detect the sketch from this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Sketch Image", func=self.scribble2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and a scribble image or a sketch image. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description"),
-            # Tool(name="Pose Detection On Image", func=self.image2pose.inference,
-            #      description="useful for when you want to detect the human pose of the image. like: generate human poses of this image, or generate a pose image from this image. "
-            #                  "The input to this tool should be a string, representing the image_path"),
-            # Tool(name="Generate Image Condition On Pose Image", func=self.pose2image.inference,
-            #      description="useful for when you want to generate a new real image from both the user desciption and a human pose image. like: generate a real image of a human from this human pose image, or generate a new real image of a human from this pose. "
-            #                  "The input to this tool should be a comma seperated string of two, representing the image_path and the user description")
-            ]
 
-    def init_agent(self, openai_api_key):
-        self.llm = OpenAI(temperature=0, openai_api_key=openai_api_key)
-        self.agent = initialize_agent(
-            self.tools,
-            self.llm,
-            agent="conversational-react-description",
-            verbose=True,
-            memory=self.memory,
-            return_intermediate_steps=True,
-            agent_kwargs={'prefix': VISUAL_CHATGPT_PREFIX, 'format_instructions': VISUAL_CHATGPT_FORMAT_INSTRUCTIONS, 'suffix': VISUAL_CHATGPT_SUFFIX}, )
+        self.models = dict()
+        for class_name, device in load_dict.items():
+            self.models[class_name] = globals()[class_name](device=device)
+
+        self.tools = []
+        for class_name, instance in self.models.items():
+            for e in dir(instance):
+                if e.startswith('inference'):
+                    func = getattr(instance, e)
+                    self.tools.append(Tool(name=func.name, description=func.description, func=func))
 
-        return gr.update(visible = True)
 
     def run_text(self, text, state):
-        print("===============Running run_text =============")
-        print("Inputs:", text, state)
-        print("======>Previous memory:\n %s" % self.agent.memory)
-        self.agent.memory.buffer = cut_dialogue_history(self.agent.memory.buffer, keep_last_n_words=400)
+        self.agent.memory.buffer = cut_dialogue_history(self.agent.memory.buffer, keep_last_n_words=500)
         res = self.agent({"input": text})
-        print("======>Current memory:\n %s" % self.agent.memory)
+        res['output'] = res['output'].replace("\\", "/")
         response = re.sub('(image/\S*png)', lambda m: f'![](/file={m.group(0)})*{m.group(0)}*', res['output'])
         state = state + [(text, response)]
-        print("Outputs:", state)
+        print(f"\nProcessed run_text, Input text: {text}\nCurrent state: {state}\n"
+              f"Current Memory: {self.agent.memory.buffer}")
         return state, state
 
     def run_image(self, image, state, txt):
-        print("===============Running run_image =============")
-        print("Inputs:", image, state)
-        print("======>Previous memory:\n %s" % self.agent.memory)
         image_filename = os.path.join('image', str(uuid.uuid4())[0:8] + ".png")
         print("======>Auto Resize Image...")
         img = Image.open(image.name)
         width, height = img.size
         ratio = min(512 / width, 512 / height)
         width_new, height_new = (round(width * ratio), round(height * ratio))
+        width_new = int(np.round(width_new / 64.0)) * 64
+        height_new = int(np.round(height_new / 64.0)) * 64
         img = img.resize((width_new, height_new))
         img = img.convert('RGB')
         img.save(image_filename, "PNG")
         print(f"Resize image form {width}x{height} to {width_new}x{height_new}")
-        description = self.i2t.inference(image_filename)
-        Human_prompt = "\nHuman: provide a figure named {}. The description is: {}. This information helps you to understand this image, but you should use tools to finish following tasks, " \
-                       "rather than directly imagine from my description. If you understand, say \"Received\". \n".format(image_filename, description)
+        description = self.models['ImageCaptioning'].inference(image_filename)
+        Human_prompt = "\nHuman: provide a figure named {}. The description is: {}. " \
+                       "This information helps you to understand this image, " \
+                       "but you should use tools to finish following tasks, " \
+                       "rather than directly imagine from my description. If you understand, say \"Received\". \n".format(
+            image_filename, description)
         AI_prompt = "Received.  "
         self.agent.memory.buffer = self.agent.memory.buffer + Human_prompt + 'AI: ' + AI_prompt
-        print("======>Current memory:\n %s" % self.agent.memory)
         state = state + [(f"![](/file={image_filename})*{image_filename}*", AI_prompt)]
-        print("Outputs:", state)
+        print(f"\nProcessed run_image, Input image: {image_filename}\nCurrent state: {state}\n"
+              f"Current Memory: {self.agent.memory.buffer}")
         return state, state, txt + ' ' + image_filename + ' '
 
-bot = ConversationBot()
+    def init_agent(self, openai_api_key):
+        self.llm = OpenAI(temperature=0, openai_api_key=openai_api_key)
+        self.agent = initialize_agent(
+            self.tools,
+            self.llm,
+            agent="conversational-react-description",
+            verbose=True,
+            memory=self.memory,
+            return_intermediate_steps=True,
+            agent_kwargs={'prefix': VISUAL_CHATGPT_PREFIX, 'format_instructions': VISUAL_CHATGPT_FORMAT_INSTRUCTIONS, 'suffix': VISUAL_CHATGPT_SUFFIX}, )
+
+        return gr.update(visible = True)
+
+bot = ConversationBot({'Text2Image':'cuda:0', 'ImageCaptioning':'cuda:0',})
+
 with gr.Blocks(css="#chatbot .overflow-y-auto{height:500px}") as demo:
     with gr.Row():
         gr.Markdown("<h3><center>Visual ChatGPT</center></h3>")

visual_foundation_models.py

@@ -16,6 +16,14 @@ from PIL import Image
 import numpy as np
 from pytorch_lightning import seed_everything
 
+def prompts(name, description):
+    def decorator(func):
+        func.name = name
+        func.description = description
+        return func
+
+    return decorator
+
 def get_new_image_name(org_img_name, func_name="update"):
     head_tail = os.path.split(org_img_name)
     head = head_tail[0]
@@ -36,9 +44,10 @@ def get_new_image_name(org_img_name, func_name="update"):
 
 class MaskFormer:
     def __init__(self, device):
+        print("Initializing MaskFormer to %s" % device)
         self.device = device
-        self.processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined", torch_dtype=torch.float16)
-        self.model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined", torch_dtype=torch.float16).to(device)
+        self.processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
+        self.model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined").to(device)
 
     def inference(self, image_path, text):
         threshold = 0.5
@@ -46,7 +55,7 @@ class MaskFormer:
         padding = 20
         original_image = Image.open(image_path)
         image = original_image.resize((512, 512))
-        inputs = self.processor(text=text, images=image, padding="max_length", return_tensors="pt",).to(self.device)
+        inputs = self.processor(text=text, images=image, padding="max_length", return_tensors="pt").to(self.device)
         with torch.no_grad():
             outputs = self.model(**inputs)
         mask = torch.sigmoid(outputs[0]).squeeze().cpu().numpy() > threshold
@@ -62,87 +71,126 @@ class MaskFormer:
         image_mask = Image.fromarray(visual_mask)
         return image_mask.resize(original_image.size)
 
+
 class ImageEditing:
     def __init__(self, device):
-        print("Initializing StableDiffusionInpaint to %s" % device)
+        print("Initializing ImageEditing to %s" % device)
         self.device = device
         self.mask_former = MaskFormer(device=self.device)
-        self.inpainting = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16).to(device)
-
-    def remove_part_of_image(self, input):
-        image_path, to_be_removed_txt = input.split(",")
-        print(f'remove_part_of_image: to_be_removed {to_be_removed_txt}')
-        return self.replace_part_of_image(f"{image_path},{to_be_removed_txt},background")
-
-    def replace_part_of_image(self, input):
-        image_path, to_be_replaced_txt, replace_with_txt = input.split(",")
-        print(f'replace_part_of_image: replace_with_txt {replace_with_txt}')
+        self.inpaint = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting").to(device)
+
+    @prompts(name="Remove Something From The Photo",
+             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. ")
+    def inference_remove(self, inputs):
+        image_path, to_be_removed_txt = inputs.split(",")
+        return self.inference_replace(f"{image_path},{to_be_removed_txt},background")
+
+    @prompts(name="Replace Something From The Photo",
+             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 ")
+    def inference_replace(self, inputs):
+        image_path, to_be_replaced_txt, replace_with_txt = inputs.split(",")
         original_image = Image.open(image_path)
         original_size = original_image.size
         mask_image = self.mask_former.inference(image_path, to_be_replaced_txt)
-        updated_image = self.inpainting(prompt=replace_with_txt, image=original_image.resize((512,512)), mask_image=mask_image.resize((512,512))).images[0]
+        updated_image = self.inpaint(prompt=replace_with_txt, image=original_image.resize((512, 512)),
+                                     mask_image=mask_image.resize((512, 512))).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="replace-something")
         updated_image = updated_image.resize(original_size)
         updated_image.save(updated_image_path)
+        print(
+            f"\nProcessed ImageEditing, Input Image: {image_path}, Replace {to_be_replaced_txt} to {replace_with_txt}, "
+            f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class Pix2Pix:
+
+class InstructPix2Pix:
     def __init__(self, device):
-        print("Initializing Pix2Pix to %s" % device)
+        print("Initializing InstructPix2Pix to %s" % device)
         self.device = device
-        self.pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix", torch_dtype=torch.float16, safety_checker=None).to(device)
+        self.pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix",
+                                                                           safety_checker=None).to(device)
         self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(self.pipe.scheduler.config)
 
+    @prompts(name="Instruct Image Using Text",
+             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. ")
     def inference(self, inputs):
         """Change style of image."""
-        print("===>Starting Pix2Pix Inference")
-        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
+        print("===>Starting InstructPix2Pix Inference")
+        image_path, text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         original_image = Image.open(image_path)
-        image = self.pipe(instruct_text,image=original_image,num_inference_steps=40,image_guidance_scale=1.2,).images[0]
+        image = self.pipe(text, image=original_image, num_inference_steps=40, image_guidance_scale=1.2).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="pix2pix")
         image.save(updated_image_path)
+        print(f"\nProcessed InstructPix2Pix, Input Image: {image_path}, Instruct Text: {text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class T2I:
+
+class Text2Image:
     def __init__(self, device):
-        print("Initializing T2I to %s" % device)
+        print("Initializing Text2Image to %s" % device)
         self.device = device
-        self.pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
-        self.text_refine_tokenizer = AutoTokenizer.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion", torch_dtype=torch.float16)
-        self.text_refine_model = AutoModelForCausalLM.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion", torch_dtype=torch.float16)
-        self.text_refine_gpt2_pipe = pipeline("text-generation", model=self.text_refine_model, tokenizer=self.text_refine_tokenizer, device=self.device, torch_dtype=torch.float16)
+        self.pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+        self.text_refine_tokenizer = AutoTokenizer.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")
+        self.text_refine_model = AutoModelForCausalLM.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")
+        self.text_refine_gpt2_pipe = pipeline("text-generation", model=self.text_refine_model,
+                                              tokenizer=self.text_refine_tokenizer, device=self.device)
         self.pipe.to(device)
 
+    @prompts(name="Generate Image From User Input Text",
+             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. ")
     def inference(self, text):
         image_filename = os.path.join('image', str(uuid.uuid4())[0:8] + ".png")
         refined_text = self.text_refine_gpt2_pipe(text)[0]["generated_text"]
-        print(f'{text} refined to {refined_text}')
         image = self.pipe(refined_text).images[0]
         image.save(image_filename)
-        print(f"Processed T2I.run, text: {text}, image_filename: {image_filename}")
+        print(
+            f"\nProcessed Text2Image, Input Text: {text}, Refined Text: {refined_text}, Output Image: {image_filename}")
         return image_filename
 
+
 class ImageCaptioning:
     def __init__(self, device):
         print("Initializing ImageCaptioning to %s" % device)
         self.device = device
-        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16)
-        self.model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to(self.device)
+        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+        self.model = BlipForConditionalGeneration.from_pretrained(
+            "Salesforce/blip-image-captioning-base").to(self.device)
 
+    @prompts(name="Get Photo Description",
+             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. ")
     def inference(self, image_path):
         inputs = self.processor(Image.open(image_path), return_tensors="pt").to(self.device)
         out = self.model.generate(**inputs)
         captions = self.processor.decode(out[0], skip_special_tokens=True)
+        print(f"\nProcessed ImageCaptioning, Input Image: {image_path}, Output Text: {captions}")
         return captions
 
-class image2canny:
-    def __init__(self):
-        print("Direct detect canny.")
+
+class Image2Canny:
+    def __init__(self, device):
+        print("Initializing Image2Canny")
         self.low_threshold = 100
         self.high_threshold = 200
 
+    @prompts(name="Edge Detection On Image",
+             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 perform 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")
     def inference(self, inputs):
-        print("===>Starting image2canny Inference")
         image = Image.open(inputs)
         image = np.array(image)
         canny = cv2.Canny(image, self.low_threshold, self.high_threshold)
@@ -151,227 +199,311 @@ class image2canny:
         canny = Image.fromarray(canny)
         updated_image_path = get_new_image_name(inputs, func_name="edge")
         canny.save(updated_image_path)
+        print(f"\nProcessed Image2Canny, Input Image: {inputs}, Output Text: {updated_image_path}")
         return updated_image_path
 
-class canny2image:
+
+class CannyText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-canny", torch_dtype=torch.float16)
+        print("Initializing CannyText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-canny")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
-        )
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
+                        'fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Canny Image",
+             description="useful when you want to generate a new real image from both the user desciption and a canny image."
+                         " like: generate a real image of a object or something from this canny image,"
+                         " or generate a new real image of a object or something from this edge image. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description. ")
     def inference(self, inputs):
-        print("===>Starting canny2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="canny2image")
         image.save(updated_image_path)
+        print(f"\nProcessed CannyText2Image, Input Canny: {image_path}, Input Text: {instruct_text}, "
+              f"Output Text: {updated_image_path}")
         return updated_image_path
 
-class image2line:
-    def __init__(self):
+
+class Image2Line:
+    def __init__(self, device):
+        print("Initializing Image2Line")
         self.detector = MLSDdetector.from_pretrained('lllyasviel/ControlNet')
 
+    @prompts(name="Line Detection On Image",
+             description="useful when you want to detect the straight line of the image. "
+                         "like: detect the straight lines of this image, or straight line detection on image, "
+                         "or peform straight line detection on this image, or detect the straight line image of this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
-        print("===>Starting image2line Inference")
         image = Image.open(inputs)
         mlsd = self.detector(image)
         updated_image_path = get_new_image_name(inputs, func_name="line-of")
         mlsd.save(updated_image_path)
+        print(f"\nProcessed Image2Line, Input Image: {inputs}, Output Line: {updated_image_path}")
         return updated_image_path
 
-class line2image:
+
+class LineText2Image:
     def __init__(self, device):
-        print("Initialize the line2image model...")
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-mlsd", torch_dtype=torch.float16)
+        print("Initializing LineText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-mlsd")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
+                        'fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Line Image",
+             description="useful when you want to generate a new real image from both the user desciption "
+                         "and a straight line image. "
+                         "like: generate a real image of a object or something from this straight line image, "
+                         "or generate a new real image of a object or something from this straight lines. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description. ")
     def inference(self, inputs):
-        print("===>Starting line2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="line2image")
         image.save(updated_image_path)
+        print(f"\nProcessed LineText2Image, Input Line: {image_path}, Input Text: {instruct_text}, "
+              f"Output Text: {updated_image_path}")
         return updated_image_path
 
-class image2hed:
-    def __init__(self):
-        print("Direct detect soft HED boundary...")
+
+class Image2Hed:
+    def __init__(self, device):
+        print("Initializing Image2Hed")
         self.detector = HEDdetector.from_pretrained('lllyasviel/ControlNet')
 
+    @prompts(name="Hed Detection On Image",
+             description="useful when you want to detect the soft hed boundary of the image. "
+                         "like: detect the soft hed boundary of this image, or hed boundary detection on image, "
+                         "or peform hed boundary detection on this image, or detect soft hed boundary image of this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
-        print("===>Starting image2hed Inference")
         image = Image.open(inputs)
         hed = self.detector(image)
         updated_image_path = get_new_image_name(inputs, func_name="hed-boundary")
         hed.save(updated_image_path)
+        print(f"\nProcessed Image2Hed, Input Image: {inputs}, Output Hed: {updated_image_path}")
         return updated_image_path
 
-class hed2image:
+
+class HedText2Image:
     def __init__(self, device):
-        print("Initialize the hed2image model...")
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-hed", torch_dtype=torch.float16)
+        print("Initializing HedText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-hed")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
+                        'fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Soft Hed Boundary Image",
+             description="useful when you want to generate a new real image from both the user desciption "
+                         "and a soft hed boundary image. "
+                         "like: generate a real image of a object or something from this soft hed boundary image, "
+                         "or generate a new real image of a object or something from this hed boundary. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting hed2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="hed2image")
         image.save(updated_image_path)
+        print(f"\nProcessed HedText2Image, Input Hed: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class image2scribble:
-    def __init__(self):
-        print("Direct detect scribble.")
+
+class Image2Scribble:
+    def __init__(self, device):
+        print("Initializing Image2Scribble")
         self.detector = HEDdetector.from_pretrained('lllyasviel/ControlNet')
 
+    @prompts(name="Sketch Detection On Image",
+             description="useful when you want to generate a scribble of the image. "
+                         "like: generate a scribble of this image, or generate a sketch from this image, "
+                         "detect the sketch from this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
-        print("===>Starting image2scribble Inference")
         image = Image.open(inputs)
         scribble = self.detector(image, scribble=True)
         updated_image_path = get_new_image_name(inputs, func_name="scribble")
         scribble.save(updated_image_path)
+        print(f"\nProcessed Image2Scribble, Input Image: {inputs}, Output Scribble: {updated_image_path}")
         return updated_image_path
 
-class scribble2image:
+
+class ScribbleText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-scribble", torch_dtype=torch.float16)
+        print("Initializing ScribbleText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-scribble")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
+                        'fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Sketch Image",
+             description="useful when you want to generate a new real image from both the user desciption and "
+                         "a scribble image or a sketch image. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting scribble2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="scribble2image")
         image.save(updated_image_path)
+        print(f"\nProcessed ScribbleText2Image, Input Scribble: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class image2pose:
-    def __init__(self):
+
+class Image2Pose:
+    def __init__(self, device):
+        print("Initializing Image2Pose")
         self.detector = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
 
+    @prompts(name="Pose Detection On Image",
+             description="useful when you want to detect the human pose of the image. "
+                         "like: generate human poses of this image, or generate a pose image from this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
-        print("===>Starting image2pose Inference")
         image = Image.open(inputs)
         pose = self.detector(image)
         updated_image_path = get_new_image_name(inputs, func_name="human-pose")
         pose.save(updated_image_path)
+        print(f"\nProcessed Image2Pose, Input Image: {inputs}, Output Pose: {updated_image_path}")
         return updated_image_path
 
-class pose2image:
+
+class PoseText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-openpose", torch_dtype=torch.float16)
+        print("Initializing PoseText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-openpose")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
-        )
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.num_inference_steps = 20
         self.seed = -1
         self.unconditional_guidance_scale = 9.0
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
+                        ' fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Pose Image",
+             description="useful when you want to generate a new real image from both the user desciption "
+                         "and a human pose image. "
+                         "like: generate a real image of a human from this human pose image, "
+                         "or generate a new real image of a human from this pose. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting pose2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="pose2image")
         image.save(updated_image_path)
+        print(f"\nProcessed PoseText2Image, Input Pose: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class image2seg:
-    def __init__(self):
-        print("Initialize image2segmentation Inference")
+
+class Image2Seg:
+    def __init__(self, device):
+        print("Initializing Image2Seg")
         self.image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
         self.image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
-
         self.ade_palette = [[120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50],
-                    [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
-                    [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
-                    [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
-                    [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
-                    [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
-                    [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
-                    [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
-                    [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
-                    [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
-                    [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
-                    [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
-                    [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
-                    [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
-                    [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255],
-                    [11, 200, 200], [255, 82, 0], [0, 255, 245], [0, 61, 255],
-                    [0, 255, 112], [0, 255, 133], [255, 0, 0], [255, 163, 0],
-                    [255, 102, 0], [194, 255, 0], [0, 143, 255], [51, 255, 0],
-                    [0, 82, 255], [0, 255, 41], [0, 255, 173], [10, 0, 255],
-                    [173, 255, 0], [0, 255, 153], [255, 92, 0], [255, 0, 255],
-                    [255, 0, 245], [255, 0, 102], [255, 173, 0], [255, 0, 20],
-                    [255, 184, 184], [0, 31, 255], [0, 255, 61], [0, 71, 255],
-                    [255, 0, 204], [0, 255, 194], [0, 255, 82], [0, 10, 255],
-                    [0, 112, 255], [51, 0, 255], [0, 194, 255], [0, 122, 255],
-                    [0, 255, 163], [255, 153, 0], [0, 255, 10], [255, 112, 0],
-                    [143, 255, 0], [82, 0, 255], [163, 255, 0], [255, 235, 0],
-                    [8, 184, 170], [133, 0, 255], [0, 255, 92], [184, 0, 255],
-                    [255, 0, 31], [0, 184, 255], [0, 214, 255], [255, 0, 112],
-                    [92, 255, 0], [0, 224, 255], [112, 224, 255], [70, 184, 160],
-                    [163, 0, 255], [153, 0, 255], [71, 255, 0], [255, 0, 163],
-                    [255, 204, 0], [255, 0, 143], [0, 255, 235], [133, 255, 0],
-                    [255, 0, 235], [245, 0, 255], [255, 0, 122], [255, 245, 0],
-                    [10, 190, 212], [214, 255, 0], [0, 204, 255], [20, 0, 255],
-                    [255, 255, 0], [0, 153, 255], [0, 41, 255], [0, 255, 204],
-                    [41, 0, 255], [41, 255, 0], [173, 0, 255], [0, 245, 255],
-                    [71, 0, 255], [122, 0, 255], [0, 255, 184], [0, 92, 255],
-                    [184, 255, 0], [0, 133, 255], [255, 214, 0], [25, 194, 194],
-                    [102, 255, 0], [92, 0, 255]]
-
+                            [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
+                            [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
+                            [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
+                            [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
+                            [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
+                            [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
+                            [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
+                            [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
+                            [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
+                            [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
+                            [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
+                            [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
+                            [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
+                            [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255],
+                            [11, 200, 200], [255, 82, 0], [0, 255, 245], [0, 61, 255],
+                            [0, 255, 112], [0, 255, 133], [255, 0, 0], [255, 163, 0],
+                            [255, 102, 0], [194, 255, 0], [0, 143, 255], [51, 255, 0],
+                            [0, 82, 255], [0, 255, 41], [0, 255, 173], [10, 0, 255],
+                            [173, 255, 0], [0, 255, 153], [255, 92, 0], [255, 0, 255],
+                            [255, 0, 245], [255, 0, 102], [255, 173, 0], [255, 0, 20],
+                            [255, 184, 184], [0, 31, 255], [0, 255, 61], [0, 71, 255],
+                            [255, 0, 204], [0, 255, 194], [0, 255, 82], [0, 10, 255],
+                            [0, 112, 255], [51, 0, 255], [0, 194, 255], [0, 122, 255],
+                            [0, 255, 163], [255, 153, 0], [0, 255, 10], [255, 112, 0],
+                            [143, 255, 0], [82, 0, 255], [163, 255, 0], [255, 235, 0],
+                            [8, 184, 170], [133, 0, 255], [0, 255, 92], [184, 0, 255],
+                            [255, 0, 31], [0, 184, 255], [0, 214, 255], [255, 0, 112],
+                            [92, 255, 0], [0, 224, 255], [112, 224, 255], [70, 184, 160],
+                            [163, 0, 255], [153, 0, 255], [71, 255, 0], [255, 0, 163],
+                            [255, 204, 0], [255, 0, 143], [0, 255, 235], [133, 255, 0],
+                            [255, 0, 235], [245, 0, 255], [255, 0, 122], [255, 245, 0],
+                            [10, 190, 212], [214, 255, 0], [0, 204, 255], [20, 0, 255],
+                            [255, 255, 0], [0, 153, 255], [0, 41, 255], [0, 255, 204],
+                            [41, 0, 255], [41, 255, 0], [173, 0, 255], [0, 245, 255],
+                            [71, 0, 255], [122, 0, 255], [0, 255, 184], [0, 92, 255],
+                            [184, 255, 0], [0, 133, 255], [255, 214, 0], [25, 194, 194],
+                            [102, 255, 0], [92, 0, 255]]
+
+    @prompts(name="Segmentation On Image",
+             description="useful when you want to detect segmentations of the image. "
+                         "like: segment this image, or generate segmentations on this image, "
+                         "or peform segmentation on this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
         image = Image.open(inputs)
         pixel_values = self.image_processor(image, return_tensors="pt").pixel_values
@@ -386,37 +518,53 @@ class image2seg:
         segmentation = Image.fromarray(color_seg)
         updated_image_path = get_new_image_name(inputs, func_name="segmentation")
         segmentation.save(updated_image_path)
+        print(f"\nProcessed Image2Pose, Input Image: {inputs}, Output Pose: {updated_image_path}")
         return updated_image_path
 
-class seg2image:
+
+class SegText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-seg", torch_dtype=torch.float16)
+        print("Initializing SegText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-seg")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
-        )
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
+                        ' fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Segmentations",
+             description="useful when you want to generate a new real image from both the user desciption and segmentations. "
+                         "like: generate a real image of a object or something from this segmentation image, "
+                         "or generate a new real image of a object or something from these segmentations. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting seg2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="segment2image")
         image.save(updated_image_path)
+        print(f"\nProcessed SegText2Image, Input Seg: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class image2depth:
-    def __init__(self):
-        print("initialize depth estimation")
+
+class Image2Depth:
+    def __init__(self, device):
+        print("Initializing Image2Depth")
         self.depth_estimator = pipeline('depth-estimation')
 
+    @prompts(name="Predict Depth On Image",
+             description="useful when you want to detect depth of the image. like: generate the depth from this image, "
+                         "or detect the depth map on this image, or predict the depth for this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
         image = Image.open(inputs)
         depth = self.depth_estimator(image)['depth']
@@ -426,38 +574,54 @@ class image2depth:
         depth = Image.fromarray(depth)
         updated_image_path = get_new_image_name(inputs, func_name="depth")
         depth.save(updated_image_path)
+        print(f"\nProcessed Image2Depth, Input Image: {inputs}, Output Depth: {updated_image_path}")
         return updated_image_path
 
-class depth2image:
+
+class DepthText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-depth", torch_dtype=torch.float16)
+        print("Initializing DepthText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-depth")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
-        )
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
+                        ' fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Depth",
+             description="useful when you want to generate a new real image from both the user desciption and depth image. "
+                         "like: generate a real image of a object or something from this depth image, "
+                         "or generate a new real image of a object or something from the depth map. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting depth2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="depth2image")
         image.save(updated_image_path)
+        print(f"\nProcessed DepthText2Image, Input Depth: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class image2normal:
-    def __init__(self):
-        print("normal estimation")
+
+class Image2Normal:
+    def __init__(self, device):
+        print("Initializing Image2Normal")
         self.depth_estimator = pipeline("depth-estimation", model="Intel/dpt-hybrid-midas")
         self.bg_threhold = 0.4
 
+    @prompts(name="Predict Normal Map On Image",
+             description="useful when you want to detect norm map of the image. "
+                         "like: generate normal map from this image, or predict normal map of this image. "
+                         "The input to this tool should be a string, representing the image_path")
     def inference(self, inputs):
         image = Image.open(inputs)
         original_size = image.size
@@ -466,13 +630,10 @@ class image2normal:
         image_depth = image.copy()
         image_depth -= np.min(image_depth)
         image_depth /= np.max(image_depth)
-
         x = cv2.Sobel(image, cv2.CV_32F, 1, 0, ksize=3)
         x[image_depth < self.bg_threhold] = 0
-
         y = cv2.Sobel(image, cv2.CV_32F, 0, 1, ksize=3)
         y[image_depth < self.bg_threhold] = 0
-
         z = np.ones_like(x) * np.pi * 2.0
         image = np.stack([x, y, z], axis=2)
         image /= np.sum(image ** 2.0, axis=2, keepdims=True) ** 0.5
@@ -481,44 +642,61 @@ class image2normal:
         image = image.resize(original_size)
         updated_image_path = get_new_image_name(inputs, func_name="normal-map")
         image.save(updated_image_path)
+        print(f"\nProcessed Image2Normal, Input Image: {inputs}, Output Depth: {updated_image_path}")
         return updated_image_path
 
-class normal2image:
+
+class NormalText2Image:
     def __init__(self, device):
-        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-normal", torch_dtype=torch.float16)
+        print("Initializing NormalText2Image to %s" % device)
+        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-normal")
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None, torch_dtype=torch.float16
-        )
+            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
         self.seed = -1
         self.a_prompt = 'best quality, extremely detailed'
-        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-
+        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
+                        ' fewer digits, cropped, worst quality, low quality'
+
+    @prompts(name="Generate Image Condition On Normal Map",
+             description="useful when you want to generate a new real image from both the user desciption and normal map. "
+                         "like: generate a real image of a object or something from this normal map, "
+                         "or generate a new real image of a object or something from the normal map. "
+                         "The input to this tool should be a comma seperated string of two, "
+                         "representing the image_path and the user description")
     def inference(self, inputs):
-        print("===>Starting normal2image Inference")
         image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
         image = Image.open(image_path)
         self.seed = random.randint(0, 65535)
         seed_everything(self.seed)
         prompt = instruct_text + ', ' + self.a_prompt
-        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt, guidance_scale=9.0).images[0]
+        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
+                          guidance_scale=9.0).images[0]
         updated_image_path = get_new_image_name(image_path, func_name="normal2image")
         image.save(updated_image_path)
+        print(f"\nProcessed NormalText2Image, Input Normal: {image_path}, Input Text: {instruct_text}, "
+              f"Output Image: {updated_image_path}")
         return updated_image_path
 
-class BLIPVQA:
+
+class VisualQuestionAnswering:
     def __init__(self, device):
-        print("Initializing BLIP VQA to %s" % device)
+        print("Initializing VisualQuestionAnswering to %s" % device)
         self.device = device
-        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base", torch_dtype=torch.float16)
-        self.model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base", torch_dtype=torch.float16).to(self.device)
+        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base")
+        self.model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base").to(self.device)
 
-    def get_answer_from_question_and_image(self, inputs):
+    @prompts(name="Answer Question About The 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")
+    def inference(self, inputs):
         image_path, question = inputs.split(",")
         raw_image = Image.open(image_path).convert('RGB')
-        print(F'BLIPVQA :question :{question}')
         inputs = self.processor(raw_image, question, return_tensors="pt").to(self.device)
         out = self.model.generate(**inputs)
         answer = self.processor.decode(out[0], skip_special_tokens=True)
+        print(f"\nProcessed VisualQuestionAnswering, Input Image: {image_path}, Input Question: {question}, "
+              f"Output Answer: {answer}")
         return answer