Upload app.py

app.py

@@ -170,7 +170,7 @@ def resize_img(input_image, max_side=640, min_side=512, size=None,
 @spaces.GPU
 def dress_process(garm_img, face_img, pose_img, prompt, cloth_guidance_scale, caption_guidance_scale,
                   face_guidance_scale,self_guidance_scale, cross_guidance_scale,if_ipa, if_post, if_control, denoise_steps, seed=42):
-    image_face_fusion = pipeline('face_fusion_torch', model='damo/cv_unet_face_fusion_torch',model_revision='v1.0.0')
+    # image_face_fusion = pipeline('face_fusion_torch', model='damo/cv_unet_face_fusion_torch',model_revision='v1.0.0')
     if prompt is None:
         prompt = "a photography of a model"
     prompt = prompt + ', best quality, high quality'
@@ -242,15 +242,15 @@ def dress_process(garm_img, face_img, pose_img, prompt, cloth_guidance_scale, ca
         num_inference_steps=denoise_steps,
     ).images
     
-    if if_post and if_ipa:
-
-        output_array = np.array(output[0])
-
-        bgr_array = cv2.cvtColor(output_array, cv2.COLOR_RGB2BGR)
-
-        bgr_image = Image.fromarray(bgr_array)
-        result = image_face_fusion(dict(template=bgr_image, user=Image.fromarray(face_image.astype('uint8'))))
-        return result[OutputKeys.OUTPUT_IMG]
+    # if if_post and if_ipa:
+    #
+    #     output_array = np.array(output[0])
+    #
+    #     bgr_array = cv2.cvtColor(output_array, cv2.COLOR_RGB2BGR)
+    #
+    #     bgr_image = Image.fromarray(bgr_array)
+    #     result = image_face_fusion(dict(template=bgr_image, user=Image.fromarray(face_image.astype('uint8'))))
+    #     return result[OutputKeys.OUTPUT_IMG]
     return output[0]
 
 
@@ -298,8 +298,8 @@ with image_blocks as demo:
                 outputs=imgs,
                 examples=face_list_path
             )
-            with gr.Row():
-                is_checked_postprocess = gr.Checkbox(label="Yes", info="Use postprocess ", value=False)
+            # with gr.Row():
+            #     is_checked_postprocess = gr.Checkbox(label="Yes", info="Use postprocess ", value=False)
 
         with gr.Column():
             pose_img = gr.Image(label="Pose", sources='upload', type="pil")