Update run/gradio_ootd.py

run/gradio_ootd.py

@@ -5,6 +5,18 @@ _ft_mod = type(sys)("torchvision.transforms.functional_tensor")
 _ft_mod.rgb_to_grayscale = _tvf.rgb_to_grayscale
 sys.modules["torchvision.transforms.functional_tensor"] = _ft_mod
 
+# Patch gradio_client bug: additionalProperties puede ser bool en JSON Schema
+from gradio_client import utils as _gc_utils
+
+_orig_get_type = _gc_utils.get_type
+
+def _patched_get_type(schema):
+    if not isinstance(schema, dict):
+        return "Any"
+    return _orig_get_type(schema)
+
+_gc_utils.get_type = _patched_get_type
+
 import spaces
 
 import gradio as gr
@@ -48,14 +60,14 @@ garment_dc = os.path.join(example_path, 'garment/048554_1.jpg')
 @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
+    category = 0
 
     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)))
@@ -64,7 +76,7 @@ def process_hd(vton_img, garm_img, n_samples, n_steps, image_scale, seed):
         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(
@@ -98,7 +110,7 @@ def process_dc(vton_img, garm_img, category, n_samples, n_steps, image_scale, se
         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)))
@@ -107,7 +119,7 @@ def process_dc(vton_img, garm_img, category, n_samples, n_steps, image_scale, se
         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(
@@ -185,11 +197,10 @@ with block:
         n_steps = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=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():
@@ -273,7 +284,7 @@ with block:
         n_steps_dc = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=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])