Upload 28 files

app.py

@@ -1,42 +1,19 @@
+from diffusion_webui.controlnet.controlnet_canny import stable_diffusion_controlnet_canny_app, stable_diffusion_controlnet_canny
+from diffusion_webui.controlnet.controlnet_depth import stable_diffusion_controlnet_depth_app, stable_diffusion_controlnet_depth
+from diffusion_webui.controlnet.controlnet_hed import stable_diffusion_controlnet_hed_app, stable_diffusion_controlnet_hed
+from diffusion_webui.controlnet.controlnet_mlsd import stable_diffusion_controlnet_mlsd_app, stable_diffusion_controlnet_mlsd
+from diffusion_webui.controlnet.controlnet_pose import stable_diffusion_controlnet_pose_app, stable_diffusion_controlnet_pose
+from diffusion_webui.controlnet.controlnet_scribble import stable_diffusion_controlnet_scribble_app, stable_diffusion_controlnet_scribble
+from diffusion_webui.controlnet.controlnet_seg import stable_diffusion_controlnet_seg_app, stable_diffusion_controlnet_seg
 
-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_canny
-from controlnet.controlnet_depth import stable_diffusion_controlnet_depth
-from controlnet.controlnet_hed import stable_diffusion_controlnet_hed
-from controlnet.controlnet_mlsd import stable_diffusion_controlnet_mlsd
-from controlnet.controlnet_pose import stable_diffusion_controlnet_pose
-from controlnet.controlnet_scribble import stable_diffusion_controlnet_scribble
-from controlnet.controlnet_seg import stable_diffusion_controlnet_seg
+from diffusion_webui.stable_diffusion.text2img_app import stable_diffusion_text2img_app, stable_diffusion_text2img
+from diffusion_webui.stable_diffusion.img2img_app import stable_diffusion_img2img_app, stable_diffusion_img2img
+from diffusion_webui.stable_diffusion.inpaint_app import stable_diffusion_inpaint_app, stable_diffusion_inpaint
 
 
 import gradio as gr
 
 
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2",
-    "stabilityai/stable-diffusion-2-base",
-    "stabilityai/stable-diffusion-2-1",
-    "stabilityai/stable-diffusion-2-1-base"
-]
-
-stable_inpiant_model_list = [
-    "stabilityai/stable-diffusion-2-inpainting",
-    "runwayml/stable-diffusion-inpainting"
-]
-
-stable_prompt_list = [
-        "a photo of a man.",
-        "a photo of a girl."
-    ]
-
-stable_negative_prompt_list = [
-        "bad, ugly",
-        "deformed"
-    ]
 app = gr.Blocks()
 with app:
     gr.Markdown("# **<h1 align='center'>Stable Diffusion + ControlNet WebUI<h1>**")
@@ -50,560 +27,153 @@ with app:
     )
     with gr.Row():
         with gr.Column():
-            with gr.Tab('Text2Image'):
-                text2image_model_id = gr.Dropdown(
-                    choices=stable_model_list, 
-                    value=stable_model_list[0], 
-                    label='Text-Image Model Id'
-                )
-
-                text2image_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_prompt_list[0], 
-                    label='Prompt'
-                )
-
-                text2image_negative_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_negative_prompt_list[0], 
-                    label='Negative Prompt'
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    text2image_guidance_scale = gr.Slider(
-                        minimum=0.1, 
-                        maximum=15, 
-                        step=0.1, 
-                        value=7.5, 
-                        label='Guidance Scale'
-                    )
-
-                    text2image_num_inference_step = gr.Slider(
-                        minimum=1, 
-                        maximum=100, 
-                        step=1, 
-                        value=50, 
-                        label='Num Inference Step'
-                    )
-
-                    text2image_height = gr.Slider(
-                        minimum=128, 
-                        maximum=1280, 
-                        step=32, 
-                        value=512, 
-                        label='Image Height'
-                    )
-
-                    text2image_width = gr.Slider(
-                        minimum=128, 
-                        maximum=1280, 
-                        step=32, 
-                        value=768, 
-                        label='Image Height'
-                    )
-
-                text2image_predict = gr.Button(value='Generator')
-
-
-            with gr.Tab('Image2Image'):
-                image2image2_image_file = gr.Image(label='Image')
-
-                image2image_model_id = gr.Dropdown(
-                    choices=stable_model_list, 
-                    value=stable_model_list[0], 
-                    label='Image-Image Model Id'
-                )
-
-                image2image_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_prompt_list[0], 
-                    label='Prompt'
-                )
-
-                image2image_negative_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_negative_prompt_list[0], 
-                    label='Negative Prompt'
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    image2image_guidance_scale = gr.Slider(
-                        minimum=0.1, 
-                        maximum=15, 
-                        step=0.1, 
-                        value=7.5, 
-                        label='Guidance Scale'
-                    )
-
-                    image2image_num_inference_step = gr.Slider(
-                        minimum=1, 
-                        maximum=100, 
-                        step=1, 
-                        value=50, 
-                        label='Num Inference Step'
-                    )
-
-                image2image_predict = gr.Button(value='Generator')
-
-            with gr.Tab('Inpaint'):
-                inpaint_image_file = gr.Image(
-                    source="upload", 
-                    type="numpy", 
-                    tool="sketch", 
-                    elem_id="source_container"
-                )
-
-                inpaint_model_id = gr.Dropdown(
-                    choices=stable_inpiant_model_list, 
-                    value=stable_inpiant_model_list[0], 
-                    label='Inpaint Model Id'
-                )
-
-                inpaint_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_prompt_list[0], 
-                    label='Prompt'
-                )
-
-                inpaint_negative_prompt = gr.Textbox(
-                    lines=1, 
-                    value=stable_negative_prompt_list[0], 
-                    label='Negative Prompt'
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    inpaint_guidance_scale = gr.Slider(
-                        minimum=0.1, 
-                        maximum=15, 
-                        step=0.1, 
-                        value=7.5, 
-                        label='Guidance Scale'
-                    )
-
-                    inpaint_num_inference_step = gr.Slider(
-                        minimum=1, 
-                        maximum=100, 
-                        step=1, 
-                        value=50, 
-                        label='Num Inference Step'
-                    )
-
-                inpaint_predict = gr.Button(value='Generator')
-
+            text2image_app = stable_diffusion_text2img_app()
+            img2img_app = stable_diffusion_img2img_app()
+            inpaint_app = stable_diffusion_inpaint_app()
+            
             with gr.Tab('ControlNet'):
-                with gr.Tab('Canny'):
-                    controlnet_canny_image_file = gr.Image(label='Image')
-
-                    controlnet_canny_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_canny_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_canny_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_canny_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_canny_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_hed_image_file = gr.Image(label='Image')
-
-                    controlnet_hed_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_hed_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_hed_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_hed_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_hed_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_mlsd_image_file = gr.Image(label='Image')
-
-                    controlnet_mlsd_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_mlsd_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_mlsd_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_mlsd_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_mlsd_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_seg_image_file = gr.Image(label='Image')
-
-                    controlnet_seg_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_seg_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_seg_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_seg_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_seg_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_depth_image_file = gr.Image(label='Image')
-
-                    controlnet_depth_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_depth_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_depth_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_depth_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_depth_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_scribble_image_file = gr.Image(label='Image')
-
-                    controlnet_scribble_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_scribble_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_scribble_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_scribble_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_scribble_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_pose_image_file = gr.Image(label='Image')
-
-                    controlnet_pose_model_id = gr.Dropdown(
-                        choices=stable_model_list, 
-                        value=stable_model_list[0], 
-                        label='Stable Model Id'
-                    )
-
-                    controlnet_pose_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_prompt_list[0], 
-                        label='Prompt'
-                    )
-
-                    controlnet_pose_negative_prompt = gr.Textbox(
-                        lines=1, 
-                        value=stable_negative_prompt_list[0], 
-                        label='Negative Prompt'
-                    )
-
-                    with gr.Accordion("Advanced Options", open=False):
-                        controlnet_pose_guidance_scale = gr.Slider(
-                            minimum=0.1, 
-                            maximum=15, 
-                            step=0.1, 
-                            value=7.5, 
-                            label='Guidance Scale'
-                        )
-
-                        controlnet_pose_num_inference_step = gr.Slider(
-                            minimum=1, 
-                            maximum=100, 
-                            step=1, 
-                            value=50, 
-                            label='Num Inference Step'
-                        )
+                controlnet_canny_app = stable_diffusion_controlnet_canny_app()
+                controlnet_hed_app = stable_diffusion_controlnet_hed_app()
+                controlnet_mlsd_app = stable_diffusion_controlnet_mlsd_app()
+                controlnet_depth_app = stable_diffusion_controlnet_depth_app()
+                controlnet_pose_app = stable_diffusion_controlnet_pose_app()
+                controlnet_scribble_app = stable_diffusion_controlnet_scribble_app()
+                controlnet_seg_app = stable_diffusion_controlnet_seg_app()
 
-                    controlnet_pose_predict = gr.Button(value='Generator')
 
-    with gr.Tab('Generator'):
+    with gr.Tab('Output'):
         with gr.Column():
             output_image = gr.Image(label='Image')
             
-        text2image_predict.click(
+        text2image_app['predict'].click(
             fn = stable_diffusion_text2img,
             inputs = [
-                text2image_model_id,
-                text2image_prompt, 
-                text2image_negative_prompt, 
-                text2image_guidance_scale,
-                text2image_num_inference_step, 
-                text2image_height,
-                text2image_width,
+                text2image_app['model_path'],
+                text2image_app['prompt'], 
+                text2image_app['negative_prompt'], 
+                text2image_app['guidance_scale'],
+                text2image_app['num_inference_step'], 
+                text2image_app['height'],
+                text2image_app['width'],
             ],
             outputs = [output_image],
         )  
 
-        image2image_predict.click(
+        img2img_app['predict'].click(
             fn = stable_diffusion_img2img,
             inputs = [
-                image2image2_image_file,
-                image2image_model_id, 
-                image2image_prompt, 
-                image2image_negative_prompt,
-                image2image_guidance_scale, 
-                image2image_num_inference_step,
+                img2img_app['image_path'],
+                img2img_app['model_path'], 
+                img2img_app['prompt'], 
+                img2img_app['negative_prompt'],
+                img2img_app['guidance_scale'], 
+                img2img_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
 
-        inpaint_predict.click(
+        inpaint_app['predict'].click(
             fn = stable_diffusion_inpaint,
             inputs = [
-                inpaint_image_file,
-                inpaint_model_id, 
-                inpaint_prompt, 
-                inpaint_negative_prompt,
-                inpaint_guidance_scale, 
-                inpaint_num_inference_step,
+                inpaint_app['image_path'],
+                inpaint_app['model_path'], 
+                inpaint_app['prompt'], 
+                inpaint_app['negative_prompt'],
+                inpaint_app['guidance_scale'], 
+                inpaint_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
 
-        controlnet_canny_predict.click(
+        controlnet_canny_app['predict'].click(
             fn = stable_diffusion_controlnet_canny,
             inputs = [
-                controlnet_canny_image_file,
-                controlnet_canny_model_id, 
-                controlnet_canny_prompt, 
-                controlnet_canny_negative_prompt,
-                controlnet_canny_guidance_scale, 
-                controlnet_canny_num_inference_step,
+                controlnet_canny_app['image_path'],
+                controlnet_canny_app['model_path'], 
+                controlnet_canny_app['prompt'], 
+                controlnet_canny_app['negative_prompt'],
+                controlnet_canny_app['guidance_scale'], 
+                controlnet_canny_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
 
-        controlnet_hed_predict.click(
+        controlnet_hed_app['predict'].click(
             fn = stable_diffusion_controlnet_hed,
             inputs = [
-                controlnet_hed_image_file,
-                controlnet_hed_model_id, 
-                controlnet_hed_prompt, 
-                controlnet_hed_negative_prompt,
-                controlnet_hed_guidance_scale, 
-                controlnet_hed_num_inference_step,
+                controlnet_hed_app['image_path'],
+                controlnet_hed_app['model_path'], 
+                controlnet_hed_app['prompt'], 
+                controlnet_hed_app['negative_prompt'],
+                controlnet_hed_app['guidance_scale'], 
+                controlnet_hed_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
         
-        controlnet_mlsd_predict.click(
+        controlnet_mlsd_app['predict'].click(
             fn = stable_diffusion_controlnet_mlsd,
             inputs = [
-                controlnet_mlsd_image_file,
-                controlnet_mlsd_model_id, 
-                controlnet_mlsd_prompt, 
-                controlnet_mlsd_negative_prompt,
-                controlnet_mlsd_guidance_scale, 
-                controlnet_mlsd_num_inference_step,
+                controlnet_mlsd_app['image_path'],
+                controlnet_mlsd_app['model_path'], 
+                controlnet_mlsd_app['prompt'], 
+                controlnet_mlsd_app['negative_prompt'],
+                controlnet_mlsd_app['guidance_scale'], 
+                controlnet_mlsd_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
         
-        controlnet_seg_predict.click(
+        controlnet_depth_app['predict'].click(
             fn = stable_diffusion_controlnet_seg,
             inputs = [
-                controlnet_seg_image_file,
-                controlnet_seg_model_id, 
-                controlnet_seg_prompt, 
-                controlnet_seg_negative_prompt,
-                controlnet_seg_guidance_scale, 
-                controlnet_seg_num_inference_step,
+                controlnet_depth_app['image_path'],
+                controlnet_depth_app['model_path'], 
+                controlnet_depth_app['prompt'], 
+                controlnet_depth_app['negative_prompt'],
+                controlnet_depth_app['guidance_scale'], 
+                controlnet_depth_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
         
-        controlnet_depth_predict.click(
+        controlnet_pose_app['predict'].click(
             fn = stable_diffusion_controlnet_depth,
             inputs = [
-                controlnet_depth_image_file,
-                controlnet_depth_model_id, 
-                controlnet_depth_prompt, 
-                controlnet_depth_negative_prompt,
-                controlnet_depth_guidance_scale, 
-                controlnet_depth_num_inference_step,
+                controlnet_pose_app['image_path'],
+                controlnet_pose_app['model_path'], 
+                controlnet_pose_app['prompt'], 
+                controlnet_pose_app['negative_prompt'],
+                controlnet_pose_app['guidance_scale'], 
+                controlnet_pose_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
         
-        controlnet_scribble_predict.click(
+        controlnet_scribble_app['predict'].click(
             fn = stable_diffusion_controlnet_scribble,
             inputs = [
-                controlnet_scribble_image_file,
-                controlnet_scribble_model_id, 
-                controlnet_scribble_prompt, 
-                controlnet_scribble_negative_prompt,
-                controlnet_scribble_guidance_scale, 
-                controlnet_scribble_num_inference_step,
+                controlnet_scribble_app['image_path'],
+                controlnet_scribble_app['model_path'], 
+                controlnet_scribble_app['prompt'], 
+                controlnet_scribble_app['negative_prompt'],
+                controlnet_scribble_app['guidance_scale'], 
+                controlnet_scribble_app['num_inference_step'],
             ],
             outputs = [output_image],
         )  
         
-        controlnet_pose_predict.click(
+        controlnet_seg_app['predict'].click(
             fn = stable_diffusion_controlnet_pose,
             inputs = [
-                controlnet_pose_image_file,
-                controlnet_pose_model_id, 
-                controlnet_pose_prompt, 
-                controlnet_pose_negative_prompt,
-                controlnet_pose_guidance_scale, 
-                controlnet_pose_num_inference_step,
+                controlnet_seg_app['image_path'],
+                controlnet_seg_app['model_path'], 
+                controlnet_seg_app['prompt'], 
+                controlnet_seg_app['negative_prompt'],
+                controlnet_seg_app['guidance_scale'], 
+                controlnet_seg_app['num_inference_step'],
             ],
             outputs = [output_image],
         )
 
-app.launch()          
+app.launch(debug=True)          

diffusion_webui/controlnet/controlnet_canny.py

@@ -0,0 +1,138 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+import cv2
+
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+def controlnet_canny(
+    image_path:str,
+):
+    image = Image.open(image_path)
+    image = np.array(image)
+
+    image = cv2.Canny(image, 100, 200)
+    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_canny(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_canny(image_path)
+    
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+
+def stable_diffusion_controlnet_canny_app():
+    with gr.Tab('Canny'):
+        controlnet_canny_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_canny_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_canny_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_canny_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_canny_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_canny_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_canny_predict = gr.Button(value='Generator')
+    
+    variables = {
+        'image_path': controlnet_canny_image_file,
+        'model_path': controlnet_canny_model_id,
+        'prompt': controlnet_canny_prompt,
+        'negative_prompt': controlnet_canny_negative_prompt,
+        'guidance_scale': controlnet_canny_guidance_scale,
+        'num_inference_step': controlnet_canny_num_inference_step,
+        'predict': controlnet_canny_predict        
+    }
+    
+    return variables

diffusion_webui/controlnet/controlnet_depth.py

@@ -0,0 +1,137 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler )
+
+from transformers import pipeline
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_depth(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_depth(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+
+def stable_diffusion_controlnet_depth_app():
+    with gr.Tab('Depth'):
+        controlnet_depth_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_depth_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_depth_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_depth_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_depth_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_depth_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_depth_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': controlnet_depth_image_file,
+        'model_path': controlnet_depth_model_id,
+        'prompt': controlnet_depth_prompt,
+        'negative_prompt': controlnet_depth_negative_prompt,
+        'guidance_scale': controlnet_depth_guidance_scale,
+        'num_inference_step': controlnet_depth_num_inference_step,
+        'predict': controlnet_depth_predict
+    }
+    
+    return variables

diffusion_webui/controlnet/controlnet_hed.py

@@ -0,0 +1,132 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from controlnet_aux import HEDdetector
+from PIL import Image
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_hed(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_hed(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+def stable_diffusion_controlnet_hed_app():
+    with gr.Tab('Hed'):
+        controlnet_hed_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_hed_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_hed_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_hed_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_hed_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_hed_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_hed_predict = gr.Button(value='Generator')
+    
+    variables = {
+        'image_path': controlnet_hed_image_file,
+        'model_path': controlnet_hed_model_id,
+        'prompt': controlnet_hed_prompt,
+        'negative_prompt': controlnet_hed_negative_prompt,
+        'guidance_scale': controlnet_hed_guidance_scale,
+        'num_inference_step': controlnet_hed_num_inference_step,
+        'predict': controlnet_hed_predict
+    }
+
+    return variables

diffusion_webui/controlnet/controlnet_mlsd.py

@@ -0,0 +1,133 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from controlnet_aux import MLSDdetector
+from PIL import Image
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_mlsd(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_mlsd(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+def stable_diffusion_controlnet_mlsd_app():
+    with gr.Tab('MLSD line'):
+        controlnet_mlsd_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_mlsd_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_mlsd_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_mlsd_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_mlsd_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_mlsd_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_mlsd_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': controlnet_mlsd_image_file,
+        'model_path': controlnet_mlsd_model_id,
+        'prompt': controlnet_mlsd_prompt,
+        'negative_prompt': controlnet_mlsd_negative_prompt,
+        'guidance_scale': controlnet_mlsd_guidance_scale,
+        'num_inference_step': controlnet_mlsd_num_inference_step,
+        'predict': controlnet_mlsd_predict
+    }
+
+    return variables
+    

diffusion_webui/controlnet/controlnet_pose.py

@@ -0,0 +1,134 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from controlnet_aux import OpenposeDetector
+
+from PIL import Image
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_pose(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_pose(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+
+def stable_diffusion_controlnet_pose_app():
+    with gr.Tab('Pose'):
+        controlnet_pose_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_pose_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_pose_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_pose_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_pose_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_pose_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_pose_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': controlnet_pose_image_file,
+        'model_path': controlnet_pose_model_id,
+        'prompt': controlnet_pose_prompt,
+        'negative_prompt': controlnet_pose_negative_prompt,
+        'guidance_scale': controlnet_pose_guidance_scale,
+        'num_inference_step': controlnet_pose_num_inference_step,
+        'predict': controlnet_pose_predict
+    }
+    
+    return variables

diffusion_webui/controlnet/controlnet_scribble.py

@@ -0,0 +1,132 @@
+from diffusers import ( StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+from controlnet_aux import HEDdetector
+
+from PIL import Image
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_scribble(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_scribble(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+def stable_diffusion_controlnet_scribble_app():
+    with gr.Tab('Scribble'):
+        controlnet_scribble_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_scribble_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_scribble_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_scribble_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_scribble_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_scribble_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_scribble_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': controlnet_scribble_image_file,
+        'model_path': controlnet_scribble_model_id,
+        'prompt': controlnet_scribble_prompt,
+        'negative_prompt': controlnet_scribble_negative_prompt,
+        'guidance_scale': controlnet_scribble_guidance_scale,
+        'num_inference_step': controlnet_scribble_num_inference_step,
+        'predict': controlnet_scribble_predict
+    }
+    
+    return variables

diffusion_webui/controlnet/controlnet_seg.py

@@ -0,0 +1,191 @@
+from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
+import torch
+from diffusers import (StableDiffusionControlNetPipeline, 
+                       ControlNetModel, UniPCMultistepScheduler)
+
+
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+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_seg(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    controlnet, image = controlnet_mlsd(image_path=image_path)
+
+    pipe = StableDiffusionControlNetPipeline.from_pretrained(
+        pretrained_model_name_or_path=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_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+def stable_diffusion_controlnet_seg_app():
+    with gr.Tab('Segmentation'):
+        controlnet_seg_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        controlnet_seg_model_id = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Stable Model Id'
+        )
+
+        controlnet_seg_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        controlnet_seg_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            controlnet_seg_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            controlnet_seg_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        controlnet_seg_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': controlnet_seg_image_file,
+        'model_path': controlnet_seg_model_id,
+        'prompt': controlnet_seg_prompt,
+        'negative_prompt': controlnet_seg_negative_prompt,
+        'guidance_scale': controlnet_seg_guidance_scale,
+        'num_inference_step': controlnet_seg_num_inference_step,
+        'predict': controlnet_seg_predict,
+    }
+    
+    return variables

diffusion_webui/stable_diffusion/img2img_app.py

@@ -0,0 +1,116 @@
+from diffusers import StableDiffusionImg2ImgPipeline, DDIMScheduler
+
+from PIL import Image
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+def stable_diffusion_img2img(
+    model_path:str,
+    image_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    image = Image.open(image_path)
+
+    pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
+        model_path, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    )
+    pipe.to("cuda")
+    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        negative_prompt = negative_prompt,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+
+def stable_diffusion_img2img_app():
+    with gr.Tab('Image2Image'):
+        image2image2_image_file = gr.Image(
+            type='filepath', 
+            label='Image'
+        )
+
+        image2image_model_path = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Image-Image Model Id'
+        )
+
+        image2image_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        image2image_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            image2image_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            image2image_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        image2image_predict = gr.Button(value='Generator')
+
+    variables = {
+        'image_path': image2image2_image_file,
+        'model_path': image2image_model_path,
+        'prompt': image2image_prompt,
+        'negative_prompt': image2image_negative_prompt,
+        'guidance_scale': image2image_guidance_scale,
+        'num_inference_step': image2image_num_inference_step,
+        'predict': image2image_predict
+    }
+
+    return variables

diffusion_webui/stable_diffusion/inpaint_app.py

@@ -0,0 +1,136 @@
+from diffusers import DiffusionPipeline, DDIMScheduler
+from PIL import Image
+import imageio
+import torch
+
+import gradio as gr
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+
+def resize(height,img):
+  baseheight = height
+  img = Image.open(img)
+  hpercent = (baseheight/float(img.size[1]))
+  wsize = int((float(img.size[0])*float(hpercent)))
+  img = img.resize((wsize,baseheight), Image.Resampling.LANCZOS)
+  return img
+
+def img_preprocces(source_img, prompt, negative_prompt):
+    imageio.imwrite("data.png", source_img["image"])
+    imageio.imwrite("data_mask.png", source_img["mask"])
+    src = resize(512, "data.png")
+    src.save("src.png")
+    mask = resize(512, "data_mask.png")  
+    mask.save("mask.png")
+    return src, mask
+
+def stable_diffusion_inpaint(
+    image_path:str,
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    ):
+
+    image, mask_image = img_preprocces(image_path, prompt, negative_prompt)
+    pipe = DiffusionPipeline.from_pretrained(
+        model_path,
+        revision="fp16",
+        torch_dtype=torch.float16,
+    )
+    pipe.to('cuda')
+    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    output = pipe(
+        prompt = prompt,
+        image = image,
+        mask_image=mask_image,
+        negative_prompt = negative_prompt,
+        num_inference_steps = num_inference_step,
+        guidance_scale = guidance_scale,
+    ).images
+
+    return output[0]
+
+
+def stable_diffusion_inpaint_app():
+    with gr.Tab('Inpaint'):
+        inpaint_image_file = gr.Image(
+            source="upload", 
+            type="numpy", 
+            tool="sketch", 
+            elem_id="source_container"
+        )
+
+        inpaint_model_id = gr.Dropdown(
+            choices=stable_inpiant_model_list, 
+            value=stable_inpiant_model_list[0], 
+            label='Inpaint Model Id'
+        )
+
+        inpaint_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        inpaint_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            inpaint_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            inpaint_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+        inpaint_predict = gr.Button(value='Generator')
+    
+    variables = {
+        "image_path": inpaint_image_file,
+        "model_path": inpaint_model_id,
+        "prompt": inpaint_prompt,
+        "negative_prompt": inpaint_negative_prompt,
+        "guidance_scale": inpaint_guidance_scale,
+        "num_inference_step": inpaint_num_inference_step,
+        "predict": inpaint_predict
+    }
+
+    return variables

diffusion_webui/stable_diffusion/text2img_app.py

@@ -0,0 +1,125 @@
+from diffusers import StableDiffusionPipeline, DDIMScheduler
+import gradio as gr
+import torch
+
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2",
+    "stabilityai/stable-diffusion-2-base",
+    "stabilityai/stable-diffusion-2-1",
+    "stabilityai/stable-diffusion-2-1-base"
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting"
+]
+
+stable_prompt_list = [
+        "a photo of a man.",
+        "a photo of a girl."
+    ]
+
+stable_negative_prompt_list = [
+        "bad, ugly",
+        "deformed"
+    ]
+
+def stable_diffusion_text2img(
+    model_path:str,
+    prompt:str,
+    negative_prompt:str,
+    guidance_scale:int,
+    num_inference_step:int,
+    height:int,
+    width:int,
+    ):
+
+    pipe = StableDiffusionPipeline.from_pretrained(
+        model_path, 
+        safety_checker=None, 
+        torch_dtype=torch.float16
+    ).to("cuda")
+
+    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+
+    images = pipe(
+        prompt,
+        height=height,
+        width=width,
+        negative_prompt=negative_prompt,
+        num_inference_steps=num_inference_step,
+        guidance_scale=guidance_scale,
+    ).images
+
+    return images[0]
+
+def stable_diffusion_text2img_app():
+    with gr.Tab('Text2Image'):
+        text2image_model_path = gr.Dropdown(
+            choices=stable_model_list, 
+            value=stable_model_list[0], 
+            label='Text-Image Model Id'
+        )
+
+        text2image_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_prompt_list[0], 
+            label='Prompt'
+        )
+
+        text2image_negative_prompt = gr.Textbox(
+            lines=1, 
+            value=stable_negative_prompt_list[0], 
+            label='Negative Prompt'
+        )
+
+        with gr.Accordion("Advanced Options", open=False):
+            text2image_guidance_scale = gr.Slider(
+                minimum=0.1, 
+                maximum=15, 
+                step=0.1, 
+                value=7.5, 
+                label='Guidance Scale'
+            )
+
+            text2image_num_inference_step = gr.Slider(
+                minimum=1, 
+                maximum=100, 
+                step=1, 
+                value=50, 
+                label='Num Inference Step'
+            )
+
+            text2image_height = gr.Slider(
+                minimum=128, 
+                maximum=1280, 
+                step=32, 
+                value=512, 
+                label='Image Height'
+            )
+
+            text2image_width = gr.Slider(
+                minimum=128, 
+                maximum=1280, 
+                step=32, 
+                value=768, 
+                label='Image Height'
+            )
+
+        text2image_predict = gr.Button(value='Generator')
+    
+    variables = {
+        "model_path": text2image_model_path,
+        "prompt": text2image_prompt,
+        "negative_prompt": text2image_negative_prompt,
+        "guidance_scale": text2image_guidance_scale,
+        "num_inference_step": text2image_num_inference_step,
+        "height": text2image_height,
+        "width": text2image_width,
+        "predict": text2image_predict
+    }
+
+    return variables 
+

requirements.txt

@@ -3,4 +3,6 @@ bitsandbytes==0.35.0
 xformers 
 controlnet_aux 
 diffusers
-imageio
+imageio
+gradio
+triton