Upload app.py

app.py

@@ -54,8 +54,8 @@ tokenizer = CLIPTokenizer.from_pretrained("SG161222/Realistic_Vision_V4.0_noVAE"
 text_encoder = CLIPTextModel.from_pretrained("SG161222/Realistic_Vision_V4.0_noVAE", subfolder="text_encoder").to(dtype=torch.float16, device=args.device)
 image_encoder = CLIPVisionModelWithProjection.from_pretrained("h94/IP-Adapter", subfolder="models/image_encoder").to(dtype=torch.float16, device=args.device)
 unet = UNet2DConditionModel.from_pretrained("SG161222/Realistic_Vision_V4.0_noVAE", subfolder="unet").to(dtype=torch.float16,device=args.device)
-image_face_fusion = pipeline('face_fusion_torch', model='damo/cv_unet_face_fusion_torch',
-                                     model_revision='v1.0.3', device='cpu')
+# image_face_fusion = pipeline('face_fusion_torch', model='damo/cv_unet_face_fusion_torch',
+#                                      model_revision='v1.0.3', device='cpu')
 #face_model
 app = FaceAnalysis(model_path="buffalo_l", providers=[('CUDAExecutionProvider', {"device_id": args.device})]) ##使用GPU:0, 默认使用buffalo_l就可以了
 app.prepare(ctx_id=0, det_size=(640, 640))
@@ -163,7 +163,8 @@ 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='v1.0.3', device='cpu')
     if prompt is None:
         prompt = "a photography of a model"
     prompt = prompt + ', best quality, high quality'