init

handler.py

@@ -54,116 +54,115 @@ class EndpointHandler():
         hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")
 
         print("Model dir: ", model_dir)
-        pass
-        # 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(),
-        # ])
-
-        # self.controlnet_identitynet = ControlNetModel.from_pretrained(
-        #     controlnet_path, torch_dtype=dtype
-        # )
-
-        # pretrained_model_name_or_path = "wangqixun/YamerMIX_v8"
-
-        # self.pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
-        # pretrained_model_name_or_path,
-        # controlnet=[self.controlnet_identitynet],
-        # torch_dtype=dtype,
-        # safety_checker=None,
-        # feature_extractor=None,
-        # ).to(device)
-
-
-        # self.pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(
-        #     self.pipe.scheduler.config
-        # )
-
-        # # load and disable LCM
-        # self.pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
-        # self.pipe.disable_lora()
-
-        # self.pipe.cuda()
-        # self.pipe.load_ip_adapter_instantid(face_adapter)
-        # self.pipe.image_proj_model.to("cuda")
-        # self.pipe.unet.to("cuda")
-
-
-        # # 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")
+        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(),
+        ])
+
+        self.controlnet_identitynet = ControlNetModel.from_pretrained(
+            controlnet_path, torch_dtype=dtype
+        )
+
+        pretrained_model_name_or_path = "wangqixun/YamerMIX_v8"
+
+        self.pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
+        pretrained_model_name_or_path,
+        controlnet=[self.controlnet_identitynet],
+        torch_dtype=dtype,
+        safety_checker=None,
+        feature_extractor=None,
+        ).to(device)
+
+
+        self.pipe.scheduler = diffusers.EulerDiscreteScheduler.from_config(
+            self.pipe.scheduler.config
+        )
+
+        # load and disable LCM
+        self.pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
+        self.pipe.disable_lora()
+
+        self.pipe.cuda()
+        self.pipe.load_ip_adapter_instantid(face_adapter)
+        self.pipe.image_proj_model.to("cuda")
+        self.pipe.unet.to("cuda")
+
+
+        # 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")
         
-        # 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": get_canny_image,
-        #     "depth": controlnet_depth,
-        # }
-
-        # 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.app = FaceAnalysis(
-        #     name="antelopev2",
-        #     root="./",
-        #     providers=["CPUExecutionProvider"],
-        # )
-        # self.app.prepare(ctx_id=0, det_size=(640, 640))
+        self.controlnet_map = {
+            "pose": controlnet_pose,
+            "canny": get_canny_image,
+            "depth": controlnet_depth,
+        }
+
+        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.app = FaceAnalysis(
+            name="antelopev2",
+            root="./",
+            providers=["CPUExecutionProvider"],
+        )
+        self.app.prepare(ctx_id=0, det_size=(640, 640))
         
     def __call__(self, param):
         print("Param: ", param)