Upload 8 files

app.py

@@ -1,8 +1,20 @@
+
 from utils.image2image import stable_diffusion_img2img
 from utils.text2image import stable_diffusion_text2img
 from utils.inpaint import stable_diffusion_inpaint
+
+from controlnet.controlnet_canny import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_depth import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_hed import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_mlsd import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_pose import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_scribble import stable_diffusion_controlnet_img2img
+from controlnet.controlnet_seg import stable_diffusion_controlnet_img2img
+
+
 import gradio as gr
 
+
 stable_model_list = [
     "runwayml/stable-diffusion-v1-5",
     "stabilityai/stable-diffusion-2",
@@ -27,7 +39,7 @@ stable_negative_prompt_list = [
     ]
 app = gr.Blocks()
 with app:
-    gr.Markdown("# **<h2 align='center'>Stable Diffusion + ControlNet WebUI<h2>**")
+    gr.Markdown("# **<h2 align='center'>Stable Diffusion WebUI<h2>**")
     gr.Markdown(
         """
         <h5 style='text-align: center'>
@@ -178,6 +190,288 @@ with app:
 
                 inpaint_predict = gr.Button(value='Generator')
 
+
+            with gr.Tab('ControlNet'):
+                with gr.Tab('Canny'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_canny_predict = gr.Button(value='Generator')
+
+                with gr.Tab('Hed'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_hed_predict = gr.Button(value='Generator')
+
+                with gr.Tab('MLSD line'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_mlsd_predict = gr.Button(value='Generator')
+
+                with gr.Tab('Segmentation'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_seg_predict = gr.Button(value='Generator')
+
+                with gr.Tab('Depth'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_depth_predict = gr.Button(value='Generator')
+
+                with gr.Tab('Scribble'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_scribble_predict = gr.Button(value='Generator')
+
+                with gr.Tab('Pose'):
+                    controlnet_image_file = gr.Image(label='Image')
+
+                    controlnet_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list, 
+                        value=stable_inpiant_model_list[0], 
+                        label='Stable Model Id'
+                    )
+
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_prompt_list[0], 
+                        label='Prompt'
+                    )
+
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, 
+                        value=stable_negative_prompt_list[0], 
+                        label='Negative Prompt'
+                    )
+
+                    with gr.Accordion("Advanced Options", open=False):
+                        controlnet_guidance_scale = gr.Slider(
+                            minimum=0.1, 
+                            maximum=15, 
+                            step=0.1, 
+                            value=7.5, 
+                            label='Guidance Scale'
+                        )
+
+                        controlnet_num_inference_step = gr.Slider(
+                            minimum=1, 
+                            maximum=100, 
+                            step=1, 
+                            value=50, 
+                            label='Num Inference Step'
+                        )
+
+                    controlnet_pose_predict = gr.Button(value='Generator')
+
     with gr.Tab('Generator'):
         with gr.Column():
             output_image = gr.Image(label='Image')
@@ -222,4 +516,91 @@ with app:
             outputs = [output_image],
         )  
 
+
+        controlnet_canny_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+
+        controlnet_hed_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+        controlnet_mlsd_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+        controlnet_seg_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+        controlnet_depth_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+        controlnet_scribble_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+        controlnet_pose_predict.click(
+            fn = stable_diffusion_controlnet_img2img,
+            inputs = [
+                inpaint_image_file,
+                inpaint_model_id, 
+                inpaint_prompt, 
+                inpaint_negative_prompt,
+                inpaint_guidance_scale, 
+                inpaint_num_inference_step,
+            ],
+            outputs = [output_image],
+        )  
+
 app.launch()          

controlnet/controlnet_canny.py

@@ -0,0 +1,66 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from PIL import Image
+import numpy as np
+import torch
+import cv2
+
+
+def controlnet_canny(
+    image_path:str,
+    low_th:int,
+    high_th:int,
+):
+    image = Image.open(image_path)
+    image = np.array(image)
+
+    image = cv2.Canny(image, low_th, high_th)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    image = Image.fromarray(image)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "lllyasviel/sd-controlnet-canny", 
+        torch_dtype=torch.float16
+    )
+    return controlnet, image
+
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    low_th:int,
+    high_th:int
+    ):
+
+    controlnet, image = controlnet_canny(
+        image_path=image_path,
+        low_th=low_th,
+        high_th=high_th
+    )
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16,
+    )
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_depth.py

@@ -0,0 +1,59 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler,
+                       DDIMScheduler)
+
+from transformers import pipeline
+from PIL import Image
+import numpy as np
+import torch
+
+
+def controlnet_depth(image_path:str):
+    depth_estimator = pipeline('depth-estimation')
+
+    image = Image.open(image_path)
+    image = depth_estimator(image)['depth']
+    image = np.array(image)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    image = Image.fromarray(image)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-depth", torch_dtype=torch.float16
+    )
+
+    return controlnet, image
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_depth(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_hed.py

@@ -0,0 +1,57 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler,
+                       DDIMScheduler)
+
+from controlnet_aux import HEDdetector
+from PIL import Image
+import numpy as np
+import torch
+import cv2
+
+
+def controlnet_hed(image_path:str):
+    hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
+
+    image = Image.open(image_path)
+    image = hed(image)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-hed", 
+        torch_dtype=torch.float16
+    )
+    return controlnet, image
+
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_hed(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_mlsd.py

@@ -0,0 +1,57 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler,
+                       DDIMScheduler)
+
+from controlnet_aux import MLSDdetector
+from PIL import Image
+import numpy as np
+import torch
+import cv2
+
+
+def controlnet_mlsd(image_path:str):
+    mlsd = MLSDdetector.from_pretrained('lllyasviel/ControlNet')
+
+    image = Image.open(image_path)
+    image = mlsd(image)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-mlsd", 
+        torch_dtype=torch.float16
+    )
+
+    return controlnet, image
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_mlsd(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_pose.py

@@ -0,0 +1,55 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from controlnet_aux import OpenposeDetector
+
+from PIL import Image
+import torch
+
+
+def controlnet_pose(image_path:str):
+    openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
+
+    image = Image.open(image_path)
+    image = openpose(image)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-openpose", 
+        torch_dtype=torch.float16
+    )
+
+    return controlnet, image
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_pose(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_scribble.py

@@ -0,0 +1,55 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler,
+                       DDIMScheduler)
+
+from controlnet_aux import HEDdetector
+
+from PIL import Image
+import torch
+
+
+def controlnet_scribble(image_path:str):
+    hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
+
+    image = Image.open(image_path)
+    image = hed(image, scribble=True)
+
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-scribble", torch_dtype=torch.float16
+    )
+
+    return controlnet, image
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_scribble(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output

controlnet/controlnet_seg.py

@@ -0,0 +1,113 @@
+from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
+import torch
+from diffusers import (StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+
+from PIL import Image
+import numpy as np
+import torch
+
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [[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]]
+
+
+def controlnet_mlsd(image_path:str):
+    image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
+    image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
+
+    image = Image.open(image_path).convert('RGB')
+    pixel_values = image_processor(image, return_tensors="pt").pixel_values
+
+    with torch.no_grad():
+        outputs = image_segmentor(pixel_values)
+
+    seg = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+
+    color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8)
+    palette = np.array(ade_palette())
+
+    for label, color in enumerate(palette):
+        color_seg[seg == label, :] = color
+
+    color_seg = color_seg.astype(np.uint8)
+    image = Image.fromarray(color_seg)
+    controlnet = ControlNetModel.from_pretrained(
+        "fusing/stable-diffusion-v1-5-controlnet-seg", torch_dtype=torch.float16
+    )
+
+    return controlnet, image
+
+
+def stable_diffusion_controlnet_img2img(
+    stable_model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    num_samples:int,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_mlsd(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=stable_model_path, 
+        controlnet=controlnet, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+
+    pipe.to("cuda")
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_images_per_prompt = num_samples,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output