Upload 78 files

run/gradio_ootd.py

@@ -1,260 +1,274 @@
-import gradio as gr
-import os
-from pathlib import Path
-import sys
-import torch
-from PIL import Image, ImageOps
-
-from utils_ootd import get_mask_location
-
-PROJECT_ROOT = Path(__file__).absolute().parents[1].absolute()
-sys.path.insert(0, str(PROJECT_ROOT))
-
-import time
-from preprocess.openpose.run_openpose import OpenPose
-from preprocess.humanparsing.run_parsing import Parsing
-from ootd.inference_ootd_hd import OOTDiffusionHD
-from ootd.inference_ootd_dc import OOTDiffusionDC
-
-
-openpose_model_hd = OpenPose(0)
-parsing_model_hd = Parsing(0)
-ootd_model_hd = OOTDiffusionHD(0)
-
-openpose_model_dc = OpenPose(1)
-parsing_model_dc = Parsing(1)
-ootd_model_dc = OOTDiffusionDC(1)
-
-
-category_dict = ['upperbody', 'lowerbody', 'dress']
-category_dict_utils = ['upper_body', 'lower_body', 'dresses']
-
-
-example_path = os.path.join(os.path.dirname(__file__), 'examples')
-model_hd = os.path.join(example_path, 'model/model_1.png')
-garment_hd = os.path.join(example_path, 'garment/03244_00.jpg')
-model_dc = os.path.join(example_path, 'model/model_8.png')
-garment_dc = os.path.join(example_path, 'garment/048554_1.jpg')
-
-def process_hd(vton_img, garm_img, n_samples, n_steps, image_scale, seed):
-    model_type = 'hd'
-    category = 0 # 0:upperbody; 1:lowerbody; 2:dress
-
-    with torch.no_grad():
-        garm_img = Image.open(garm_img).resize((768, 1024))
-        vton_img = Image.open(vton_img).resize((768, 1024))
-        keypoints = openpose_model_hd(vton_img.resize((384, 512)))
-        model_parse, _ = parsing_model_hd(vton_img.resize((384, 512)))
-
-        mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
-        mask = mask.resize((768, 1024), Image.NEAREST)
-        mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
-        
-        masked_vton_img = Image.composite(mask_gray, vton_img, mask)
-
-        images = ootd_model_hd(
-            model_type=model_type,
-            category=category_dict[category],
-            image_garm=garm_img,
-            image_vton=masked_vton_img,
-            mask=mask,
-            image_ori=vton_img,
-            num_samples=n_samples,
-            num_steps=n_steps,
-            image_scale=image_scale,
-            seed=seed,
-        )
-
-    return images
-
-def process_dc(vton_img, garm_img, category, n_samples, n_steps, image_scale, seed):
-    model_type = 'dc'
-    if category == 'Upper-body':
-        category = 0
-    elif category == 'Lower-body':
-        category = 1
-    else:
-        category =2
-
-    with torch.no_grad():
-        garm_img = Image.open(garm_img).resize((768, 1024))
-        vton_img = Image.open(vton_img).resize((768, 1024))
-        keypoints = openpose_model_dc(vton_img.resize((384, 512)))
-        model_parse, _ = parsing_model_dc(vton_img.resize((384, 512)))
-
-        mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
-        mask = mask.resize((768, 1024), Image.NEAREST)
-        mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
-        
-        masked_vton_img = Image.composite(mask_gray, vton_img, mask)
-
-        images = ootd_model_dc(
-            model_type=model_type,
-            category=category_dict[category],
-            image_garm=garm_img,
-            image_vton=masked_vton_img,
-            mask=mask,
-            image_ori=vton_img,
-            num_samples=n_samples,
-            num_steps=n_steps,
-            image_scale=image_scale,
-            seed=seed,
-        )
-
-    return images
-
-
-block = gr.Blocks().queue()
-with block:
-    with gr.Row():
-        gr.Markdown("# OOTDiffusion Demo")
-    with gr.Row():
-        gr.Markdown("## Half-body")
-    with gr.Row():
-        gr.Markdown("***Support upper-body garments***")
-    with gr.Row():
-        with gr.Column():
-            vton_img = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_hd)
-            example = gr.Examples(
-                inputs=vton_img,
-                examples_per_page=14,
-                examples=[
-                    os.path.join(example_path, 'model/model_1.png'),
-                    os.path.join(example_path, 'model/model_2.png'),
-                    os.path.join(example_path, 'model/model_3.png'),
-                    os.path.join(example_path, 'model/model_4.png'),
-                    os.path.join(example_path, 'model/model_5.png'),
-                    os.path.join(example_path, 'model/model_6.png'),
-                    os.path.join(example_path, 'model/model_7.png'),
-                    os.path.join(example_path, 'model/01008_00.jpg'),
-                    os.path.join(example_path, 'model/07966_00.jpg'),
-                    os.path.join(example_path, 'model/05997_00.jpg'),
-                    os.path.join(example_path, 'model/02849_00.jpg'),
-                    os.path.join(example_path, 'model/14627_00.jpg'),
-                    os.path.join(example_path, 'model/09597_00.jpg'),
-                    os.path.join(example_path, 'model/01861_00.jpg'),
-                ])
-        with gr.Column():
-            garm_img = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_hd)
-            example = gr.Examples(
-                inputs=garm_img,
-                examples_per_page=14,
-                examples=[
-                    os.path.join(example_path, 'garment/03244_00.jpg'),
-                    os.path.join(example_path, 'garment/00126_00.jpg'),
-                    os.path.join(example_path, 'garment/03032_00.jpg'),
-                    os.path.join(example_path, 'garment/06123_00.jpg'),
-                    os.path.join(example_path, 'garment/02305_00.jpg'),
-                    os.path.join(example_path, 'garment/00055_00.jpg'),
-                    os.path.join(example_path, 'garment/00470_00.jpg'),
-                    os.path.join(example_path, 'garment/02015_00.jpg'),
-                    os.path.join(example_path, 'garment/10297_00.jpg'),
-                    os.path.join(example_path, 'garment/07382_00.jpg'),
-                    os.path.join(example_path, 'garment/07764_00.jpg'),
-                    os.path.join(example_path, 'garment/00151_00.jpg'),
-                    os.path.join(example_path, 'garment/12562_00.jpg'),
-                    os.path.join(example_path, 'garment/04825_00.jpg'),
-                ])
-        with gr.Column():
-            result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)   
-    with gr.Column():
-        run_button = gr.Button(value="Run")
-        n_samples = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
-        n_steps = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
-        # scale = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
-        image_scale = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
-        seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
-        
-    ips = [vton_img, garm_img, n_samples, n_steps, image_scale, seed]
-    run_button.click(fn=process_hd, inputs=ips, outputs=[result_gallery])
-
-
-    with gr.Row():
-        gr.Markdown("## Full-body")
-    with gr.Row():
-        gr.Markdown("***Support upper-body/lower-body/dresses; garment category must be paired!!!***")
-    with gr.Row():
-        with gr.Column():
-            vton_img_dc = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_dc)
-            example = gr.Examples(
-                label="Examples (upper-body/lower-body)",
-                inputs=vton_img_dc,
-                examples_per_page=7,
-                examples=[
-                    os.path.join(example_path, 'model/model_8.png'),
-                    os.path.join(example_path, 'model/049447_0.jpg'),
-                    os.path.join(example_path, 'model/049713_0.jpg'),
-                    os.path.join(example_path, 'model/051482_0.jpg'),
-                    os.path.join(example_path, 'model/051918_0.jpg'),
-                    os.path.join(example_path, 'model/051962_0.jpg'),
-                    os.path.join(example_path, 'model/049205_0.jpg'),
-                ])
-            example = gr.Examples(
-                label="Examples (dress)",
-                inputs=vton_img_dc,
-                examples_per_page=7,
-                examples=[
-                    os.path.join(example_path, 'model/model_9.png'),
-                    os.path.join(example_path, 'model/052767_0.jpg'),
-                    os.path.join(example_path, 'model/052472_0.jpg'),
-                    os.path.join(example_path, 'model/053514_0.jpg'),
-                    os.path.join(example_path, 'model/053228_0.jpg'),
-                    os.path.join(example_path, 'model/052964_0.jpg'),
-                    os.path.join(example_path, 'model/053700_0.jpg'),
-                ])
-        with gr.Column():
-            garm_img_dc = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_dc)
-            category_dc = gr.Dropdown(label="Garment category (important option!!!)", choices=["Upper-body", "Lower-body", "Dress"], value="Upper-body")
-            example = gr.Examples(
-                label="Examples (upper-body)",
-                inputs=garm_img_dc,
-                examples_per_page=7,
-                examples=[
-                    os.path.join(example_path, 'garment/048554_1.jpg'),
-                    os.path.join(example_path, 'garment/049920_1.jpg'),
-                    os.path.join(example_path, 'garment/049965_1.jpg'),
-                    os.path.join(example_path, 'garment/049949_1.jpg'),
-                    os.path.join(example_path, 'garment/050181_1.jpg'),
-                    os.path.join(example_path, 'garment/049805_1.jpg'),
-                    os.path.join(example_path, 'garment/050105_1.jpg'),
-                ])
-            example = gr.Examples(
-                label="Examples (lower-body)",
-                inputs=garm_img_dc,
-                examples_per_page=7,
-                examples=[
-                    os.path.join(example_path, 'garment/051827_1.jpg'),
-                    os.path.join(example_path, 'garment/051946_1.jpg'),
-                    os.path.join(example_path, 'garment/051473_1.jpg'),
-                    os.path.join(example_path, 'garment/051515_1.jpg'),
-                    os.path.join(example_path, 'garment/051517_1.jpg'),
-                    os.path.join(example_path, 'garment/051988_1.jpg'),
-                    os.path.join(example_path, 'garment/051412_1.jpg'),
-                ])
-            example = gr.Examples(
-                label="Examples (dress)",
-                inputs=garm_img_dc,
-                examples_per_page=7,
-                examples=[
-                    os.path.join(example_path, 'garment/053290_1.jpg'),
-                    os.path.join(example_path, 'garment/053744_1.jpg'),
-                    os.path.join(example_path, 'garment/053742_1.jpg'),
-                    os.path.join(example_path, 'garment/053786_1.jpg'),
-                    os.path.join(example_path, 'garment/053790_1.jpg'),
-                    os.path.join(example_path, 'garment/053319_1.jpg'),
-                    os.path.join(example_path, 'garment/052234_1.jpg'),
-                ])
-        with gr.Column():
-            result_gallery_dc = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)   
-    with gr.Column():
-        run_button_dc = gr.Button(value="Run")
-        n_samples_dc = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
-        n_steps_dc = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
-        # scale_dc = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
-        image_scale_dc = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
-        seed_dc = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
-        
-    ips_dc = [vton_img_dc, garm_img_dc, category_dc, n_samples_dc, n_steps_dc, image_scale_dc, seed_dc]
-    run_button_dc.click(fn=process_dc, inputs=ips_dc, outputs=[result_gallery_dc])
-
-block.launch(server_name='0.0.0.0', server_port=7865)
+import gradio as gr
+import os
+from pathlib import Path
+import sys
+import torch
+from PIL import Image, ImageOps
+
+from utils_ootd import get_mask_location
+
+PROJECT_ROOT = Path(__file__).absolute().parents[1].absolute()
+sys.path.insert(0, str(PROJECT_ROOT))
+
+from preprocess.openpose.run_openpose import OpenPose
+from preprocess.humanparsing.run_parsing import Parsing
+from ootd.inference_ootd_hd import OOTDiffusionHD
+from ootd.inference_ootd_dc import OOTDiffusionDC
+
+
+openpose_model_hd = OpenPose(0)
+parsing_model_hd = Parsing(0)
+ootd_model_hd = OOTDiffusionHD(0)
+
+openpose_model_dc = OpenPose(1)
+parsing_model_dc = Parsing(1)
+ootd_model_dc = OOTDiffusionDC(1)
+
+
+category_dict = ['upperbody', 'lowerbody', 'dress']
+category_dict_utils = ['upper_body', 'lower_body', 'dresses']
+
+
+example_path = os.path.join(os.path.dirname(__file__), 'examples')
+model_hd = os.path.join(example_path, 'model/model_1.png')
+garment_hd = os.path.join(example_path, 'garment/03244_00.jpg')
+model_dc = os.path.join(example_path, 'model/model_8.png')
+garment_dc = os.path.join(example_path, 'garment/048554_1.jpg')
+
+
+import spaces
+
+@spaces.GPU
+def process_hd(vton_img, garm_img, n_samples, n_steps, image_scale, seed):
+    model_type = 'hd'
+    category = 0 # 0:upperbody; 1:lowerbody; 2:dress
+
+    with torch.no_grad():
+        openpose_model_hd.preprocessor.body_estimation.model.to('cuda')
+        ootd_model_hd.pipe.to('cuda')
+        ootd_model_hd.image_encoder.to('cuda')
+        ootd_model_hd.text_encoder.to('cuda')
+        
+        garm_img = Image.open(garm_img).resize((768, 1024))
+        vton_img = Image.open(vton_img).resize((768, 1024))
+        keypoints = openpose_model_hd(vton_img.resize((384, 512)))
+        model_parse, _ = parsing_model_hd(vton_img.resize((384, 512)))
+
+        mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
+        mask = mask.resize((768, 1024), Image.NEAREST)
+        mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
+        
+        masked_vton_img = Image.composite(mask_gray, vton_img, mask)
+
+        images = ootd_model_hd(
+            model_type=model_type,
+            category=category_dict[category],
+            image_garm=garm_img,
+            image_vton=masked_vton_img,
+            mask=mask,
+            image_ori=vton_img,
+            num_samples=n_samples,
+            num_steps=n_steps,
+            image_scale=image_scale,
+            seed=seed,
+        )
+
+    return images
+
+@spaces.GPU
+def process_dc(vton_img, garm_img, category, n_samples, n_steps, image_scale, seed):
+    model_type = 'dc'
+    if category == 'Upper-body':
+        category = 0
+    elif category == 'Lower-body':
+        category = 1
+    else:
+        category =2
+
+    with torch.no_grad():
+        openpose_model_dc.preprocessor.body_estimation.model.to('cuda')
+        ootd_model_dc.pipe.to('cuda')
+        ootd_model_dc.image_encoder.to('cuda')
+        ootd_model_dc.text_encoder.to('cuda')
+        
+        garm_img = Image.open(garm_img).resize((768, 1024))
+        vton_img = Image.open(vton_img).resize((768, 1024))
+        keypoints = openpose_model_dc(vton_img.resize((384, 512)))
+        model_parse, _ = parsing_model_dc(vton_img.resize((384, 512)))
+
+        mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
+        mask = mask.resize((768, 1024), Image.NEAREST)
+        mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
+        
+        masked_vton_img = Image.composite(mask_gray, vton_img, mask)
+
+        images = ootd_model_dc(
+            model_type=model_type,
+            category=category_dict[category],
+            image_garm=garm_img,
+            image_vton=masked_vton_img,
+            mask=mask,
+            image_ori=vton_img,
+            num_samples=n_samples,
+            num_steps=n_steps,
+            image_scale=image_scale,
+            seed=seed,
+        )
+
+    return images
+
+
+block = gr.Blocks().queue()
+with block:
+    with gr.Row():
+        gr.Markdown("# OOTDiffusion Demo")
+    with gr.Row():
+        gr.Markdown("## Half-body")
+    with gr.Row():
+        gr.Markdown("***Support upper-body garments***")
+    with gr.Row():
+        with gr.Column():
+            vton_img = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_hd)
+            example = gr.Examples(
+                inputs=vton_img,
+                examples_per_page=14,
+                examples=[
+                    os.path.join(example_path, 'model/model_1.png'),
+                    os.path.join(example_path, 'model/model_2.png'),
+                    os.path.join(example_path, 'model/model_3.png'),
+                    os.path.join(example_path, 'model/model_4.png'),
+                    os.path.join(example_path, 'model/model_5.png'),
+                    os.path.join(example_path, 'model/model_6.png'),
+                    os.path.join(example_path, 'model/model_7.png'),
+                    os.path.join(example_path, 'model/01008_00.jpg'),
+                    os.path.join(example_path, 'model/07966_00.jpg'),
+                    os.path.join(example_path, 'model/05997_00.jpg'),
+                    os.path.join(example_path, 'model/02849_00.jpg'),
+                    os.path.join(example_path, 'model/14627_00.jpg'),
+                    os.path.join(example_path, 'model/09597_00.jpg'),
+                    os.path.join(example_path, 'model/01861_00.jpg'),
+                ])
+        with gr.Column():
+            garm_img = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_hd)
+            example = gr.Examples(
+                inputs=garm_img,
+                examples_per_page=14,
+                examples=[
+                    os.path.join(example_path, 'garment/03244_00.jpg'),
+                    os.path.join(example_path, 'garment/00126_00.jpg'),
+                    os.path.join(example_path, 'garment/03032_00.jpg'),
+                    os.path.join(example_path, 'garment/06123_00.jpg'),
+                    os.path.join(example_path, 'garment/02305_00.jpg'),
+                    os.path.join(example_path, 'garment/00055_00.jpg'),
+                    os.path.join(example_path, 'garment/00470_00.jpg'),
+                    os.path.join(example_path, 'garment/02015_00.jpg'),
+                    os.path.join(example_path, 'garment/10297_00.jpg'),
+                    os.path.join(example_path, 'garment/07382_00.jpg'),
+                    os.path.join(example_path, 'garment/07764_00.jpg'),
+                    os.path.join(example_path, 'garment/00151_00.jpg'),
+                    os.path.join(example_path, 'garment/12562_00.jpg'),
+                    os.path.join(example_path, 'garment/04825_00.jpg'),
+                ])
+        with gr.Column():
+            result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)   
+    with gr.Column():
+        run_button = gr.Button(value="Run")
+        n_samples = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
+        n_steps = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
+        # scale = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
+        image_scale = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
+        seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
+        
+    ips = [vton_img, garm_img, n_samples, n_steps, image_scale, seed]
+    run_button.click(fn=process_hd, inputs=ips, outputs=[result_gallery])
+
+
+    with gr.Row():
+        gr.Markdown("## Full-body")
+    with gr.Row():
+        gr.Markdown("***Support upper-body/lower-body/dresses; garment category must be paired!!!***")
+    with gr.Row():
+        with gr.Column():
+            vton_img_dc = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_dc)
+            example = gr.Examples(
+                label="Examples (upper-body/lower-body)",
+                inputs=vton_img_dc,
+                examples_per_page=7,
+                examples=[
+                    os.path.join(example_path, 'model/model_8.png'),
+                    os.path.join(example_path, 'model/049447_0.jpg'),
+                    os.path.join(example_path, 'model/049713_0.jpg'),
+                    os.path.join(example_path, 'model/051482_0.jpg'),
+                    os.path.join(example_path, 'model/051918_0.jpg'),
+                    os.path.join(example_path, 'model/051962_0.jpg'),
+                    os.path.join(example_path, 'model/049205_0.jpg'),
+                ])
+            example = gr.Examples(
+                label="Examples (dress)",
+                inputs=vton_img_dc,
+                examples_per_page=7,
+                examples=[
+                    os.path.join(example_path, 'model/model_9.png'),
+                    os.path.join(example_path, 'model/052767_0.jpg'),
+                    os.path.join(example_path, 'model/052472_0.jpg'),
+                    os.path.join(example_path, 'model/053514_0.jpg'),
+                    os.path.join(example_path, 'model/053228_0.jpg'),
+                    os.path.join(example_path, 'model/052964_0.jpg'),
+                    os.path.join(example_path, 'model/053700_0.jpg'),
+                ])
+        with gr.Column():
+            garm_img_dc = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_dc)
+            category_dc = gr.Dropdown(label="Garment category (important option!!!)", choices=["Upper-body", "Lower-body", "Dress"], value="Upper-body")
+            example = gr.Examples(
+                label="Examples (upper-body)",
+                inputs=garm_img_dc,
+                examples_per_page=7,
+                examples=[
+                    os.path.join(example_path, 'garment/048554_1.jpg'),
+                    os.path.join(example_path, 'garment/049920_1.jpg'),
+                    os.path.join(example_path, 'garment/049965_1.jpg'),
+                    os.path.join(example_path, 'garment/049949_1.jpg'),
+                    os.path.join(example_path, 'garment/050181_1.jpg'),
+                    os.path.join(example_path, 'garment/049805_1.jpg'),
+                    os.path.join(example_path, 'garment/050105_1.jpg'),
+                ])
+            example = gr.Examples(
+                label="Examples (lower-body)",
+                inputs=garm_img_dc,
+                examples_per_page=7,
+                examples=[
+                    os.path.join(example_path, 'garment/051827_1.jpg'),
+                    os.path.join(example_path, 'garment/051946_1.jpg'),
+                    os.path.join(example_path, 'garment/051473_1.jpg'),
+                    os.path.join(example_path, 'garment/051515_1.jpg'),
+                    os.path.join(example_path, 'garment/051517_1.jpg'),
+                    os.path.join(example_path, 'garment/051988_1.jpg'),
+                    os.path.join(example_path, 'garment/051412_1.jpg'),
+                ])
+            example = gr.Examples(
+                label="Examples (dress)",
+                inputs=garm_img_dc,
+                examples_per_page=7,
+                examples=[
+                    os.path.join(example_path, 'garment/053290_1.jpg'),
+                    os.path.join(example_path, 'garment/053744_1.jpg'),
+                    os.path.join(example_path, 'garment/053742_1.jpg'),
+                    os.path.join(example_path, 'garment/053786_1.jpg'),
+                    os.path.join(example_path, 'garment/053790_1.jpg'),
+                    os.path.join(example_path, 'garment/053319_1.jpg'),
+                    os.path.join(example_path, 'garment/052234_1.jpg'),
+                ])
+        with gr.Column():
+            result_gallery_dc = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)   
+    with gr.Column():
+        run_button_dc = gr.Button(value="Run")
+        n_samples_dc = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
+        n_steps_dc = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
+        # scale_dc = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
+        image_scale_dc = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
+        seed_dc = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
+        
+    ips_dc = [vton_img_dc, garm_img_dc, category_dc, n_samples_dc, n_steps_dc, image_scale_dc, seed_dc]
+    run_button_dc.click(fn=process_dc, inputs=ips_dc, outputs=[result_gallery_dc])
+
+block.launch()

run/run_ootd.py

@@ -1,87 +1,87 @@
-from pathlib import Path
-import sys
-from PIL import Image
-from utils_ootd import get_mask_location
-
-PROJECT_ROOT = Path(__file__).absolute().parents[1].absolute()
-sys.path.insert(0, str(PROJECT_ROOT))
-
-from preprocess.openpose.run_openpose import OpenPose
-from preprocess.humanparsing.run_parsing import Parsing
-from ootd.inference_ootd_hd import OOTDiffusionHD
-from ootd.inference_ootd_dc import OOTDiffusionDC
-
-
-import argparse
-parser = argparse.ArgumentParser(description='run ootd')
-parser.add_argument('--gpu_id', '-g', type=int, default=0, required=False)
-parser.add_argument('--model_path', type=str, default="", required=True)
-parser.add_argument('--cloth_path', type=str, default="", required=True)
-parser.add_argument('--model_type', type=str, default="hd", required=False)
-parser.add_argument('--category', '-c', type=int, default=0, required=False)
-parser.add_argument('--scale', type=float, default=2.0, required=False)
-parser.add_argument('--step', type=int, default=20, required=False)
-parser.add_argument('--sample', type=int, default=4, required=False)
-parser.add_argument('--seed', type=int, default=-1, required=False)
-args = parser.parse_args()
-
-
-openpose_model = OpenPose(args.gpu_id)
-parsing_model = Parsing(args.gpu_id)
-
-
-category_dict = ['upperbody', 'lowerbody', 'dress']
-category_dict_utils = ['upper_body', 'lower_body', 'dresses']
-
-model_type = args.model_type # "hd" or "dc"
-category = args.category # 0:upperbody; 1:lowerbody; 2:dress
-cloth_path = args.cloth_path
-model_path = args.model_path
-
-image_scale = args.scale
-n_steps = args.step
-n_samples = args.sample
-seed = args.seed
-
-if model_type == "hd":
-    model = OOTDiffusionHD(args.gpu_id)
-elif model_type == "dc":
-    model = OOTDiffusionDC(args.gpu_id)
-else:
-    raise ValueError("model_type must be \'hd\' or \'dc\'!")
-
-
-if __name__ == '__main__':
-
-    if model_type == 'hd' and category != 0:
-        raise ValueError("model_type \'hd\' requires category == 0 (upperbody)!")
-
-    cloth_img = Image.open(cloth_path).resize((768, 1024))
-    model_img = Image.open(model_path).resize((768, 1024))
-    keypoints = openpose_model(model_img.resize((384, 512)))
-    model_parse, _ = parsing_model(model_img.resize((384, 512)))
-
-    mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
-    mask = mask.resize((768, 1024), Image.NEAREST)
-    mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
-    
-    masked_vton_img = Image.composite(mask_gray, model_img, mask)
-    masked_vton_img.save('./images_output/mask.jpg')
-
-    images = model(
-        model_type=model_type,
-        category=category_dict[category],
-        image_garm=cloth_img,
-        image_vton=masked_vton_img,
-        mask=mask,
-        image_ori=model_img,
-        num_samples=n_samples,
-        num_steps=n_steps,
-        image_scale=image_scale,
-        seed=seed,
-    )
-
-    image_idx = 0
-    for image in images:
-        image.save('./images_output/out_' + model_type + '_' + str(image_idx) + '.png')
-        image_idx += 1
+from pathlib import Path
+import sys
+from PIL import Image
+from utils_ootd import get_mask_location
+
+PROJECT_ROOT = Path(__file__).absolute().parents[1].absolute()
+sys.path.insert(0, str(PROJECT_ROOT))
+
+from preprocess.openpose.run_openpose import OpenPose
+from preprocess.humanparsing.run_parsing import Parsing
+from ootd.inference_ootd_hd import OOTDiffusionHD
+from ootd.inference_ootd_dc import OOTDiffusionDC
+
+
+import argparse
+parser = argparse.ArgumentParser(description='run ootd')
+parser.add_argument('--gpu_id', '-g', type=int, default=0, required=False)
+parser.add_argument('--model_path', type=str, default="", required=True)
+parser.add_argument('--cloth_path', type=str, default="", required=True)
+parser.add_argument('--model_type', type=str, default="hd", required=False)
+parser.add_argument('--category', '-c', type=int, default=0, required=False)
+parser.add_argument('--scale', type=float, default=2.0, required=False)
+parser.add_argument('--step', type=int, default=20, required=False)
+parser.add_argument('--sample', type=int, default=4, required=False)
+parser.add_argument('--seed', type=int, default=-1, required=False)
+args = parser.parse_args()
+
+
+openpose_model = OpenPose(args.gpu_id)
+parsing_model = Parsing(args.gpu_id)
+
+
+category_dict = ['upperbody', 'lowerbody', 'dress']
+category_dict_utils = ['upper_body', 'lower_body', 'dresses']
+
+model_type = args.model_type # "hd" or "dc"
+category = args.category # 0:upperbody; 1:lowerbody; 2:dress
+cloth_path = args.cloth_path
+model_path = args.model_path
+
+image_scale = args.scale
+n_steps = args.step
+n_samples = args.sample
+seed = args.seed
+
+if model_type == "hd":
+    model = OOTDiffusionHD(args.gpu_id)
+elif model_type == "dc":
+    model = OOTDiffusionDC(args.gpu_id)
+else:
+    raise ValueError("model_type must be \'hd\' or \'dc\'!")
+
+
+if __name__ == '__main__':
+
+    if model_type == 'hd' and category != 0:
+        raise ValueError("model_type \'hd\' requires category == 0 (upperbody)!")
+
+    cloth_img = Image.open(cloth_path).resize((768, 1024))
+    model_img = Image.open(model_path).resize((768, 1024))
+    keypoints = openpose_model(model_img.resize((384, 512)))
+    model_parse, _ = parsing_model(model_img.resize((384, 512)))
+
+    mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
+    mask = mask.resize((768, 1024), Image.NEAREST)
+    mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
+    
+    masked_vton_img = Image.composite(mask_gray, model_img, mask)
+    masked_vton_img.save('./images_output/mask.jpg')
+
+    images = model(
+        model_type=model_type,
+        category=category_dict[category],
+        image_garm=cloth_img,
+        image_vton=masked_vton_img,
+        mask=mask,
+        image_ori=model_img,
+        num_samples=n_samples,
+        num_steps=n_steps,
+        image_scale=image_scale,
+        seed=seed,
+    )
+
+    image_idx = 0
+    for image in images:
+        image.save('./images_output/out_' + model_type + '_' + str(image_idx) + '.png')
+        image_idx += 1

run/utils_ootd.py

@@ -1,170 +1,170 @@
-import pdb
-
-import numpy as np
-import cv2
-from PIL import Image, ImageDraw
-
-label_map = {
-    "background": 0,
-    "hat": 1,
-    "hair": 2,
-    "sunglasses": 3,
-    "upper_clothes": 4,
-    "skirt": 5,
-    "pants": 6,
-    "dress": 7,
-    "belt": 8,
-    "left_shoe": 9,
-    "right_shoe": 10,
-    "head": 11,
-    "left_leg": 12,
-    "right_leg": 13,
-    "left_arm": 14,
-    "right_arm": 15,
-    "bag": 16,
-    "scarf": 17,
-}
-
-def extend_arm_mask(wrist, elbow, scale):
-  wrist = elbow + scale * (wrist - elbow)
-  return wrist
-
-def hole_fill(img):
-    img = np.pad(img[1:-1, 1:-1], pad_width = 1, mode = 'constant', constant_values=0)
-    img_copy = img.copy()
-    mask = np.zeros((img.shape[0] + 2, img.shape[1] + 2), dtype=np.uint8)
-
-    cv2.floodFill(img, mask, (0, 0), 255)
-    img_inverse = cv2.bitwise_not(img)
-    dst = cv2.bitwise_or(img_copy, img_inverse)
-    return dst
-
-def refine_mask(mask):
-    contours, hierarchy = cv2.findContours(mask.astype(np.uint8),
-                                           cv2.RETR_CCOMP, cv2.CHAIN_APPROX_TC89_L1)
-    area = []
-    for j in range(len(contours)):
-        a_d = cv2.contourArea(contours[j], True)
-        area.append(abs(a_d))
-    refine_mask = np.zeros_like(mask).astype(np.uint8)
-    if len(area) != 0:
-        i = area.index(max(area))
-        cv2.drawContours(refine_mask, contours, i, color=255, thickness=-1)
-
-    return refine_mask
-
-def get_mask_location(model_type, category, model_parse: Image.Image, keypoint: dict, width=384,height=512):
-    im_parse = model_parse.resize((width, height), Image.NEAREST)
-    parse_array = np.array(im_parse)
-
-    if model_type == 'hd':
-        arm_width = 60
-    elif model_type == 'dc':
-        arm_width = 45
-    else:
-        raise ValueError("model_type must be \'hd\' or \'dc\'!")
-
-    parse_head = (parse_array == 1).astype(np.float32) + \
-                 (parse_array == 3).astype(np.float32) + \
-                 (parse_array == 11).astype(np.float32)
-
-    parser_mask_fixed = (parse_array == label_map["left_shoe"]).astype(np.float32) + \
-                        (parse_array == label_map["right_shoe"]).astype(np.float32) + \
-                        (parse_array == label_map["hat"]).astype(np.float32) + \
-                        (parse_array == label_map["sunglasses"]).astype(np.float32) + \
-                        (parse_array == label_map["bag"]).astype(np.float32)
-
-    parser_mask_changeable = (parse_array == label_map["background"]).astype(np.float32)
-
-    arms_left = (parse_array == 14).astype(np.float32)
-    arms_right = (parse_array == 15).astype(np.float32)
-    arms = arms_left + arms_right
-
-    if category == 'dresses':
-        parse_mask = (parse_array == 7).astype(np.float32) + \
-                     (parse_array == 4).astype(np.float32) + \
-                     (parse_array == 5).astype(np.float32) + \
-                     (parse_array == 6).astype(np.float32)
-
-        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
-
-    elif category == 'upper_body':
-        parse_mask = (parse_array == 4).astype(np.float32) + (parse_array == 7).astype(np.float32)
-        parser_mask_fixed_lower_cloth = (parse_array == label_map["skirt"]).astype(np.float32) + \
-                                        (parse_array == label_map["pants"]).astype(np.float32)
-        parser_mask_fixed += parser_mask_fixed_lower_cloth
-        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
-    elif category == 'lower_body':
-        parse_mask = (parse_array == 6).astype(np.float32) + \
-                     (parse_array == 12).astype(np.float32) + \
-                     (parse_array == 13).astype(np.float32) + \
-                     (parse_array == 5).astype(np.float32)
-        parser_mask_fixed += (parse_array == label_map["upper_clothes"]).astype(np.float32) + \
-                             (parse_array == 14).astype(np.float32) + \
-                             (parse_array == 15).astype(np.float32)
-        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
-    else:
-        raise NotImplementedError
-
-    # Load pose points
-    pose_data = keypoint["pose_keypoints_2d"]
-    pose_data = np.array(pose_data)
-    pose_data = pose_data.reshape((-1, 2))
-
-    im_arms_left = Image.new('L', (width, height))
-    im_arms_right = Image.new('L', (width, height))
-    arms_draw_left = ImageDraw.Draw(im_arms_left)
-    arms_draw_right = ImageDraw.Draw(im_arms_right)
-    if category == 'dresses' or category == 'upper_body':
-        shoulder_right = np.multiply(tuple(pose_data[2][:2]), height / 512.0)
-        shoulder_left = np.multiply(tuple(pose_data[5][:2]), height / 512.0)
-        elbow_right = np.multiply(tuple(pose_data[3][:2]), height / 512.0)
-        elbow_left = np.multiply(tuple(pose_data[6][:2]), height / 512.0)
-        wrist_right = np.multiply(tuple(pose_data[4][:2]), height / 512.0)
-        wrist_left = np.multiply(tuple(pose_data[7][:2]), height / 512.0)
-        ARM_LINE_WIDTH = int(arm_width / 512 * height)
-        size_left = [shoulder_left[0] - ARM_LINE_WIDTH // 2, shoulder_left[1] - ARM_LINE_WIDTH // 2, shoulder_left[0] + ARM_LINE_WIDTH // 2, shoulder_left[1] + ARM_LINE_WIDTH // 2]
-        size_right = [shoulder_right[0] - ARM_LINE_WIDTH // 2, shoulder_right[1] - ARM_LINE_WIDTH // 2, shoulder_right[0] + ARM_LINE_WIDTH // 2,
-                      shoulder_right[1] + ARM_LINE_WIDTH // 2]
-        
-
-        if wrist_right[0] <= 1. and wrist_right[1] <= 1.:
-            im_arms_right = arms_right
-        else:
-            wrist_right = extend_arm_mask(wrist_right, elbow_right, 1.2)
-            arms_draw_right.line(np.concatenate((shoulder_right, elbow_right, wrist_right)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
-            arms_draw_right.arc(size_right, 0, 360, 'white', ARM_LINE_WIDTH // 2)
-
-        if wrist_left[0] <= 1. and wrist_left[1] <= 1.:
-            im_arms_left = arms_left
-        else:
-            wrist_left = extend_arm_mask(wrist_left, elbow_left, 1.2)
-            arms_draw_left.line(np.concatenate((wrist_left, elbow_left, shoulder_left)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
-            arms_draw_left.arc(size_left, 0, 360, 'white', ARM_LINE_WIDTH // 2)
-
-        hands_left = np.logical_and(np.logical_not(im_arms_left), arms_left)
-        hands_right = np.logical_and(np.logical_not(im_arms_right), arms_right)
-        parser_mask_fixed += hands_left + hands_right
-
-    parser_mask_fixed = np.logical_or(parser_mask_fixed, parse_head)
-    parse_mask = cv2.dilate(parse_mask, np.ones((5, 5), np.uint16), iterations=5)
-    if category == 'dresses' or category == 'upper_body':
-        neck_mask = (parse_array == 18).astype(np.float32)
-        neck_mask = cv2.dilate(neck_mask, np.ones((5, 5), np.uint16), iterations=1)
-        neck_mask = np.logical_and(neck_mask, np.logical_not(parse_head))
-        parse_mask = np.logical_or(parse_mask, neck_mask)
-        arm_mask = cv2.dilate(np.logical_or(im_arms_left, im_arms_right).astype('float32'), np.ones((5, 5), np.uint16), iterations=4)
-        parse_mask += np.logical_or(parse_mask, arm_mask)
-
-    parse_mask = np.logical_and(parser_mask_changeable, np.logical_not(parse_mask))
-
-    parse_mask_total = np.logical_or(parse_mask, parser_mask_fixed)
-    inpaint_mask = 1 - parse_mask_total
-    img = np.where(inpaint_mask, 255, 0)
-    dst = hole_fill(img.astype(np.uint8))
-    dst = refine_mask(dst)
-    inpaint_mask = dst / 255 * 1
-    mask = Image.fromarray(inpaint_mask.astype(np.uint8) * 255)
-    mask_gray = Image.fromarray(inpaint_mask.astype(np.uint8) * 127)
-
-    return mask, mask_gray
+import pdb
+
+import numpy as np
+import cv2
+from PIL import Image, ImageDraw
+
+label_map = {
+    "background": 0,
+    "hat": 1,
+    "hair": 2,
+    "sunglasses": 3,
+    "upper_clothes": 4,
+    "skirt": 5,
+    "pants": 6,
+    "dress": 7,
+    "belt": 8,
+    "left_shoe": 9,
+    "right_shoe": 10,
+    "head": 11,
+    "left_leg": 12,
+    "right_leg": 13,
+    "left_arm": 14,
+    "right_arm": 15,
+    "bag": 16,
+    "scarf": 17,
+}
+
+def extend_arm_mask(wrist, elbow, scale):
+  wrist = elbow + scale * (wrist - elbow)
+  return wrist
+
+def hole_fill(img):
+    img = np.pad(img[1:-1, 1:-1], pad_width = 1, mode = 'constant', constant_values=0)
+    img_copy = img.copy()
+    mask = np.zeros((img.shape[0] + 2, img.shape[1] + 2), dtype=np.uint8)
+
+    cv2.floodFill(img, mask, (0, 0), 255)
+    img_inverse = cv2.bitwise_not(img)
+    dst = cv2.bitwise_or(img_copy, img_inverse)
+    return dst
+
+def refine_mask(mask):
+    contours, hierarchy = cv2.findContours(mask.astype(np.uint8),
+                                           cv2.RETR_CCOMP, cv2.CHAIN_APPROX_TC89_L1)
+    area = []
+    for j in range(len(contours)):
+        a_d = cv2.contourArea(contours[j], True)
+        area.append(abs(a_d))
+    refine_mask = np.zeros_like(mask).astype(np.uint8)
+    if len(area) != 0:
+        i = area.index(max(area))
+        cv2.drawContours(refine_mask, contours, i, color=255, thickness=-1)
+
+    return refine_mask
+
+def get_mask_location(model_type, category, model_parse: Image.Image, keypoint: dict, width=384,height=512):
+    im_parse = model_parse.resize((width, height), Image.NEAREST)
+    parse_array = np.array(im_parse)
+
+    if model_type == 'hd':
+        arm_width = 60
+    elif model_type == 'dc':
+        arm_width = 45
+    else:
+        raise ValueError("model_type must be \'hd\' or \'dc\'!")
+
+    parse_head = (parse_array == 1).astype(np.float32) + \
+                 (parse_array == 3).astype(np.float32) + \
+                 (parse_array == 11).astype(np.float32)
+
+    parser_mask_fixed = (parse_array == label_map["left_shoe"]).astype(np.float32) + \
+                        (parse_array == label_map["right_shoe"]).astype(np.float32) + \
+                        (parse_array == label_map["hat"]).astype(np.float32) + \
+                        (parse_array == label_map["sunglasses"]).astype(np.float32) + \
+                        (parse_array == label_map["bag"]).astype(np.float32)
+
+    parser_mask_changeable = (parse_array == label_map["background"]).astype(np.float32)
+
+    arms_left = (parse_array == 14).astype(np.float32)
+    arms_right = (parse_array == 15).astype(np.float32)
+    arms = arms_left + arms_right
+
+    if category == 'dresses':
+        parse_mask = (parse_array == 7).astype(np.float32) + \
+                     (parse_array == 4).astype(np.float32) + \
+                     (parse_array == 5).astype(np.float32) + \
+                     (parse_array == 6).astype(np.float32)
+
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+
+    elif category == 'upper_body':
+        parse_mask = (parse_array == 4).astype(np.float32) + (parse_array == 7).astype(np.float32)
+        parser_mask_fixed_lower_cloth = (parse_array == label_map["skirt"]).astype(np.float32) + \
+                                        (parse_array == label_map["pants"]).astype(np.float32)
+        parser_mask_fixed += parser_mask_fixed_lower_cloth
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+    elif category == 'lower_body':
+        parse_mask = (parse_array == 6).astype(np.float32) + \
+                     (parse_array == 12).astype(np.float32) + \
+                     (parse_array == 13).astype(np.float32) + \
+                     (parse_array == 5).astype(np.float32)
+        parser_mask_fixed += (parse_array == label_map["upper_clothes"]).astype(np.float32) + \
+                             (parse_array == 14).astype(np.float32) + \
+                             (parse_array == 15).astype(np.float32)
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+    else:
+        raise NotImplementedError
+
+    # Load pose points
+    pose_data = keypoint["pose_keypoints_2d"]
+    pose_data = np.array(pose_data)
+    pose_data = pose_data.reshape((-1, 2))
+
+    im_arms_left = Image.new('L', (width, height))
+    im_arms_right = Image.new('L', (width, height))
+    arms_draw_left = ImageDraw.Draw(im_arms_left)
+    arms_draw_right = ImageDraw.Draw(im_arms_right)
+    if category == 'dresses' or category == 'upper_body':
+        shoulder_right = np.multiply(tuple(pose_data[2][:2]), height / 512.0)
+        shoulder_left = np.multiply(tuple(pose_data[5][:2]), height / 512.0)
+        elbow_right = np.multiply(tuple(pose_data[3][:2]), height / 512.0)
+        elbow_left = np.multiply(tuple(pose_data[6][:2]), height / 512.0)
+        wrist_right = np.multiply(tuple(pose_data[4][:2]), height / 512.0)
+        wrist_left = np.multiply(tuple(pose_data[7][:2]), height / 512.0)
+        ARM_LINE_WIDTH = int(arm_width / 512 * height)
+        size_left = [shoulder_left[0] - ARM_LINE_WIDTH // 2, shoulder_left[1] - ARM_LINE_WIDTH // 2, shoulder_left[0] + ARM_LINE_WIDTH // 2, shoulder_left[1] + ARM_LINE_WIDTH // 2]
+        size_right = [shoulder_right[0] - ARM_LINE_WIDTH // 2, shoulder_right[1] - ARM_LINE_WIDTH // 2, shoulder_right[0] + ARM_LINE_WIDTH // 2,
+                      shoulder_right[1] + ARM_LINE_WIDTH // 2]
+        
+
+        if wrist_right[0] <= 1. and wrist_right[1] <= 1.:
+            im_arms_right = arms_right
+        else:
+            wrist_right = extend_arm_mask(wrist_right, elbow_right, 1.2)
+            arms_draw_right.line(np.concatenate((shoulder_right, elbow_right, wrist_right)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
+            arms_draw_right.arc(size_right, 0, 360, 'white', ARM_LINE_WIDTH // 2)
+
+        if wrist_left[0] <= 1. and wrist_left[1] <= 1.:
+            im_arms_left = arms_left
+        else:
+            wrist_left = extend_arm_mask(wrist_left, elbow_left, 1.2)
+            arms_draw_left.line(np.concatenate((wrist_left, elbow_left, shoulder_left)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
+            arms_draw_left.arc(size_left, 0, 360, 'white', ARM_LINE_WIDTH // 2)
+
+        hands_left = np.logical_and(np.logical_not(im_arms_left), arms_left)
+        hands_right = np.logical_and(np.logical_not(im_arms_right), arms_right)
+        parser_mask_fixed += hands_left + hands_right
+
+    parser_mask_fixed = np.logical_or(parser_mask_fixed, parse_head)
+    parse_mask = cv2.dilate(parse_mask, np.ones((5, 5), np.uint16), iterations=5)
+    if category == 'dresses' or category == 'upper_body':
+        neck_mask = (parse_array == 18).astype(np.float32)
+        neck_mask = cv2.dilate(neck_mask, np.ones((5, 5), np.uint16), iterations=1)
+        neck_mask = np.logical_and(neck_mask, np.logical_not(parse_head))
+        parse_mask = np.logical_or(parse_mask, neck_mask)
+        arm_mask = cv2.dilate(np.logical_or(im_arms_left, im_arms_right).astype('float32'), np.ones((5, 5), np.uint16), iterations=4)
+        parse_mask += np.logical_or(parse_mask, arm_mask)
+
+    parse_mask = np.logical_and(parser_mask_changeable, np.logical_not(parse_mask))
+
+    parse_mask_total = np.logical_or(parse_mask, parser_mask_fixed)
+    inpaint_mask = 1 - parse_mask_total
+    img = np.where(inpaint_mask, 255, 0)
+    dst = hole_fill(img.astype(np.uint8))
+    dst = refine_mask(dst)
+    inpaint_mask = dst / 255 * 1
+    mask = Image.fromarray(inpaint_mask.astype(np.uint8) * 255)
+    mask_gray = Image.fromarray(inpaint_mask.astype(np.uint8) * 127)
+
+    return mask, mask_gray