no control net

handler.py

@@ -57,19 +57,19 @@ class EndpointHandler():
         face_adapter = f"./checkpoints/ip-adapter.bin"
         controlnet_path = f"./checkpoints/ControlNetModel"
 
-        transform = Compose([
-            Resize(
-                width=518,
-                height=518,
-                resize_target=False,
-                keep_aspect_ratio=True,
-                ensure_multiple_of=14,
-                resize_method='lower_bound',
-                image_interpolation_method=cv2.INTER_CUBIC,
-            ),
-            NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-            PrepareForNet(),
-        ])
+        # transform = Compose([
+        #     Resize(
+        #         width=518,
+        #         height=518,
+        #         resize_target=False,
+        #         keep_aspect_ratio=True,
+        #         ensure_multiple_of=14,
+        #         resize_method='lower_bound',
+        #         image_interpolation_method=cv2.INTER_CUBIC,
+        #     ),
+        #     NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        #     PrepareForNet(),
+        # ])
 
         self.controlnet_identitynet = ControlNetModel.from_pretrained(
             controlnet_path, torch_dtype=dtype
@@ -101,61 +101,61 @@ class EndpointHandler():
 
 
         # controlnet-pose/canny/depth
-        controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
-        controlnet_canny_model = "diffusers/controlnet-canny-sdxl-1.0"
-        controlnet_depth_model = "diffusers/controlnet-depth-sdxl-1.0-small"
-
-        controlnet_pose = ControlNetModel.from_pretrained(
-            controlnet_pose_model, torch_dtype=dtype
-        ).to(device)
-        controlnet_canny = ControlNetModel.from_pretrained(
-            controlnet_canny_model, torch_dtype=dtype
-        ).to(device)
-        controlnet_depth = ControlNetModel.from_pretrained(
-            controlnet_depth_model, torch_dtype=dtype
-        ).to(device)
-
-        def get_canny_image(image, t1=100, t2=200):
-            image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
-            edges = cv2.Canny(image, t1, t2)
-            return Image.fromarray(edges, "L")
+        # controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
+        # controlnet_canny_model = "diffusers/controlnet-canny-sdxl-1.0"
+        # controlnet_depth_model = "diffusers/controlnet-depth-sdxl-1.0-small"
+
+        # controlnet_pose = ControlNetModel.from_pretrained(
+        #     controlnet_pose_model, torch_dtype=dtype
+        # ).to(device)
+        # controlnet_canny = ControlNetModel.from_pretrained(
+        #     controlnet_canny_model, torch_dtype=dtype
+        # ).to(device)
+        # controlnet_depth = ControlNetModel.from_pretrained(
+        #     controlnet_depth_model, torch_dtype=dtype
+        # ).to(device)
+
+        # def get_canny_image(image, t1=100, t2=200):
+        #     image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
+        #     edges = cv2.Canny(image, t1, t2)
+        #     return Image.fromarray(edges, "L")
         
-        def get_depth_map(image):
+        # def get_depth_map(image):
         
-            image = np.array(image) / 255.0
+        #     image = np.array(image) / 255.0
 
-            h, w = image.shape[:2]
+        #     h, w = image.shape[:2]
 
-            image = transform({'image': image})['image']
-            image = torch.from_numpy(image).unsqueeze(0).to("cuda")
+        #     image = transform({'image': image})['image']
+        #     image = torch.from_numpy(image).unsqueeze(0).to("cuda")
 
-            with torch.no_grad():
-                depth = depth_anything(image)
+        #     with torch.no_grad():
+        #         depth = depth_anything(image)
 
-            depth = F.interpolate(depth[None], (h, w), mode='bilinear', align_corners=False)[0, 0]
-            depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
+        #     depth = F.interpolate(depth[None], (h, w), mode='bilinear', align_corners=False)[0, 0]
+        #     depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
 
-            depth = depth.cpu().numpy().astype(np.uint8)
+        #     depth = depth.cpu().numpy().astype(np.uint8)
 
-            depth_image = Image.fromarray(depth)
+        #     depth_image = Image.fromarray(depth)
 
-            return depth_image
+        #     return depth_image
         
-        self.controlnet_map = {
-            "pose": controlnet_pose,
-            "canny": controlnet_canny,
-            "depth": controlnet_depth,
-        }
+        # self.controlnet_map = {
+        #     "pose": controlnet_pose,
+        #     "canny": controlnet_canny,
+        #     "depth": controlnet_depth,
+        # }
 
-        openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
-        depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_vitl14').to(device).eval()
+        # openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+        # depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_vitl14').to(device).eval()
 
 
-        self.controlnet_map_fn = {
-            "pose": openpose,
-            "canny": get_canny_image,
-            "depth": get_depth_map,
-        }
+        # self.controlnet_map_fn = {
+        #     "pose": openpose,
+        #     "canny": get_canny_image,
+        #     "depth": get_depth_map,
+        # }
         
         self.app = FaceAnalysis(name="buffalo_l", root="./", providers=["CPUExecutionProvider"])
         self.app.prepare(ctx_id=0, det_size=(640, 640))
@@ -166,10 +166,10 @@ class EndpointHandler():
         
         adapter_strength_ratio = 0.8
         identitynet_strength_ratio = 0.8
-        pose_strength = 0.4
-        canny_strength = 0.3
-        depth_strength = 0.5
-        controlnet_selection = ["pose", "canny", "depth"]
+        # pose_strength = 0.4
+        # canny_strength = 0.3
+        # depth_strength = 0.5
+        # controlnet_selection = ["pose", "canny", "depth"]
         
         face_image_path = "https://i.ibb.co/SKg69dD/kaifu-resize.png"
         pose_image_path = "https://i.ibb.co/ZSrQ8ZJ/pose.jpg"
@@ -276,27 +276,27 @@ class EndpointHandler():
         control_mask[y1:y2, x1:x2] = 255
         control_mask = Image.fromarray(control_mask.astype(np.uint8))
 
-        if len(controlnet_selection) > 0:
-            controlnet_scales = {
-                "pose": pose_strength,
-                "canny": canny_strength,
-                "depth": depth_strength,
-            }
-            self.pipe.controlnet = MultiControlNetModel(
-                [self.controlnet_identitynet]
-                + [self.controlnet_map[s] for s in controlnet_selection]
-            )
-            control_scales = [float(identitynet_strength_ratio)] + [
-                controlnet_scales[s] for s in controlnet_selection
-            ]
-            control_images = [face_kps] + [
-                self.controlnet_map_fn[s](img_controlnet).resize((width, height))
-                for s in controlnet_selection
-            ]
-        else:
-            self.pipe.controlnet = self.controlnet_identitynet
-            control_scales = float(identitynet_strength_ratio)
-            control_images = face_kps
+        # if len(controlnet_selection) > 0:
+        #     controlnet_scales = {
+        #         "pose": pose_strength,
+        #         "canny": canny_strength,
+        #         "depth": depth_strength,
+        #     }
+        #     self.pipe.controlnet = MultiControlNetModel(
+        #         [self.controlnet_identitynet]
+        #         + [self.controlnet_map[s] for s in controlnet_selection]
+        #     )
+        #     control_scales = [float(identitynet_strength_ratio)] + [
+        #         controlnet_scales[s] for s in controlnet_selection
+        #     ]
+        #     control_images = [face_kps] + [
+        #         self.controlnet_map_fn[s](img_controlnet).resize((width, height))
+        #         for s in controlnet_selection
+        #     ]
+        # else:
+        self.pipe.controlnet = self.controlnet_identitynet
+        control_scales = float(identitynet_strength_ratio)
+        control_images = face_kps
 
         generator = torch.Generator(device=device.type).manual_seed(3)