Update main.py

main.py

@@ -10,6 +10,103 @@ from vtoonify_model import Model
 app = FastAPI()
 model = Model(device='cuda' if torch.cuda.is_available() else 'cpu')
 
+    def load_model(self, style_type: str) -> tuple[torch.Tensor, str]:
+        if 'illustration' in style_type:
+            self.color_transfer = True
+        else:
+            self.color_transfer = False
+        if style_type not in self.style_types.keys():
+            return None, 'Oops, wrong Style Type. Please select a valid model.'
+        self.style_name = style_type
+        model_path, ind = self.style_types[style_type]
+        style_path = os.path.join('models',os.path.dirname(model_path),'exstyle_code.npy')
+        self.vtoonify.load_state_dict(torch.load(huggingface_hub.hf_hub_download(MODEL_REPO,'models/'+model_path), 
+                                            map_location=lambda storage, loc: storage)['g_ema'])
+        tmp = np.load(huggingface_hub.hf_hub_download(MODEL_REPO, style_path), allow_pickle=True).item()
+        exstyle = torch.tensor(tmp[list(tmp.keys())[ind]]).to(self.device)
+        with torch.no_grad():  
+            exstyle = self.vtoonify.zplus2wplus(exstyle)
+        return exstyle, 'Model of %s loaded.'%(style_type)
+    
+    def detect_and_align(self, frame, top, bottom, left, right, return_para=False):
+        message = 'Error: no face detected! Please retry or change the photo.'
+        paras = get_video_crop_parameter(frame, self.landmarkpredictor, [left, right, top, bottom])
+        instyle = None
+        h, w, scale = 0, 0, 0
+        if paras is not None:
+            h,w,top,bottom,left,right,scale = paras
+            H, W = int(bottom-top), int(right-left)
+            # for HR image, we apply gaussian blur to it to avoid over-sharp stylization results
+            kernel_1d = np.array([[0.125],[0.375],[0.375],[0.125]])
+            if scale <= 0.75:
+                frame = cv2.sepFilter2D(frame, -1, kernel_1d, kernel_1d)
+            if scale <= 0.375:
+                frame = cv2.sepFilter2D(frame, -1, kernel_1d, kernel_1d)
+            frame = cv2.resize(frame, (w, h))[top:bottom, left:right]
+            with torch.no_grad():
+                I = align_face(frame, self.landmarkpredictor)
+                if I is not None:
+                    I = self.transform(I).unsqueeze(dim=0).to(self.device)
+                    instyle = self.pspencoder(I)
+                    instyle = self.vtoonify.zplus2wplus(instyle)
+                    message = 'Successfully rescale the frame to (%d, %d)'%(bottom-top, right-left)
+                else:
+                    frame = np.zeros((256,256,3), np.uint8)
+        else:
+            frame = np.zeros((256,256,3), np.uint8)
+        if return_para:
+            return frame, instyle, message, w, h, top, bottom, left, right, scale
+        return frame, instyle, message
+    
+    #@torch.inference_mode()
+    def detect_and_align_image(self, image: str, top: int, bottom: int, left: int, right: int
+                              ) -> tuple[np.ndarray, torch.Tensor, str]:
+        if image is None:
+            return np.zeros((256,256,3), np.uint8), None, 'Error: fail to load empty file.'
+        frame = cv2.imread(image)
+        if frame is None:
+            return np.zeros((256,256,3), np.uint8), None, 'Error: fail to load the image.'       
+        frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
+        return self.detect_and_align(frame, top, bottom, left, right)
+    
+    def detect_and_align_video(self, video: str, top: int, bottom: int, left: int, right: int
+                              ) -> tuple[np.ndarray, torch.Tensor, str]:
+        if video is None:
+            return np.zeros((256,256,3), np.uint8), None, 'Error: fail to load empty file.'
+        video_cap = cv2.VideoCapture(video)
+        if video_cap.get(7) == 0:
+            video_cap.release()
+            return np.zeros((256,256,3), np.uint8), torch.zeros(1,18,512).to(self.device), 'Error: fail to load the video.'
+        success, frame = video_cap.read()
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        video_cap.release()
+        return self.detect_and_align(frame, top, bottom, left, right)
+    
+  
+    def image_toonify(self, aligned_face: np.ndarray, instyle: torch.Tensor, exstyle: torch.Tensor, style_degree: float, style_type: str) -> tuple[np.ndarray, str]:
+        #print(style_type + ' ' + self.style_name)
+        if instyle is None or aligned_face is None:
+            return np.zeros((256,256,3), np.uint8), 'Opps, something wrong with the input. Please go to Step 2 and Rescale Image/First Frame again.'
+        if self.style_name != style_type:
+            exstyle, _  = self.load_model(style_type)
+        if exstyle is None:
+            return np.zeros((256,256,3), np.uint8), 'Opps, something wrong with the style type. Please go to Step 1 and load model again.'
+        with torch.no_grad():
+            if self.color_transfer:
+                s_w = exstyle
+            else:
+                s_w = instyle.clone()
+                s_w[:,:7] = exstyle[:,:7]
+
+            x = self.transform(aligned_face).unsqueeze(dim=0).to(self.device)
+            x_p = F.interpolate(self.parsingpredictor(2*(F.interpolate(x, scale_factor=2, mode='bilinear', align_corners=False)))[0], 
+                                scale_factor=0.5, recompute_scale_factor=False).detach()
+            inputs = torch.cat((x, x_p/16.), dim=1)
+            y_tilde = self.vtoonify(inputs, s_w.repeat(inputs.size(0), 1, 1), d_s = style_degree)        
+            y_tilde = torch.clamp(y_tilde, -1, 1)
+        print('*** Toonify %dx%d image with style of %s'%(y_tilde.shape[2], y_tilde.shape[3], style_type))
+        return ((y_tilde[0].cpu().numpy().transpose(1, 2, 0) + 1.0) * 127.5).astype(np.uint8), 'Successfully toonify the image with style of %s'%(self.style_name)
+    
 @app.post("/upload/")
 async def process_image(file: UploadFile = File(...)):
     # Save the uploaded image locally
@@ -20,10 +117,9 @@ async def process_image(file: UploadFile = File(...)):
     exstyle, load_info = model.load_model('cartoon1')
 
     # Process the uploaded image
-    
-    top, bottom, left, right = 200, 200,200, 200  
+    top, bottom, left, right = 200, 200, 200, 200  
     aligned_face, _, input_info = model.detect_and_align_image("uploaded_image.jpg", top, bottom, left, right)
-    processed_image, message = model.image_toonify(aligned_face, exstyle, style_type = 'cartoon1' , style_degree=0.5)
+    processed_image, message = model.image_toonify(aligned_face, instyle=exstyle, exstyle=exstyle, style_degree=0.5, style_type='cartoon1')
 
     # Save the processed image
     with open("result_image.jpg", "wb") as result_buffer: