pushed new endpoint

handler.py

@@ -1,20 +1,69 @@
-from typing import Dict, List, Any
+from typing import  Dict, List, Any
+import torch
+from diffusers import DPMSolverMultistepScheduler, StableDiffusionInpaintPipeline
+from PIL import Image
+import base64
+from io import BytesIO
+
+
+# set device
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+if device.type != 'cuda':
+    raise ValueError("need to run on GPU")
 
 class EndpointHandler():
     def __init__(self, path=""):
-        # Preload all the elements you are going to need at inference.
-        # pseudo:
-        # self.model= load_model(path)
-        print("Loading model")
+        # load StableDiffusionInpaintPipeline pipeline
+        self.pipe = StableDiffusionInpaintPipeline.from_pretrained(path, torch_dtype=torch.float16)
+        # use DPMSolverMultistepScheduler
+        self.pipe.scheduler = DPMSolverMultistepScheduler.from_config(self.pipe.scheduler.config)
+        # move to device        
+        self.pipe = self.pipe.to(device)
 
-    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         """
-       data args:
-            inputs (:obj: `str` | `PIL.Image` | `np.array`)
-            kwargs
-      Return:
-            A :obj:`list` | `dict`: will be serialized and returned
+        :param data: A dictionary contains `inputs` and optional `image` field.
+        :return: A dictionary with `image` field contains image in base64.
         """
-
-        # pseudo
-        # self.model(input)
+        inputs = data.pop("inputs", data)
+        encoded_image = data.pop("image", None)
+        encoded_mask_image = data.pop("mask_image", None)
+        
+        # hyperparamters
+        num_inference_steps = data.pop("num_inference_steps", 25)
+        guidance_scale = data.pop("guidance_scale", 7.5)
+        negative_prompt = data.pop("negative_prompt", None)
+        height = data.pop("height", None)
+        width = data.pop("width", None)
+        
+        # process image
+        if encoded_image is not None and encoded_mask_image is not None:
+            image = self.decode_base64_image(encoded_image)
+            mask_image = self.decode_base64_image(encoded_mask_image)
+        else:
+            image = None
+            mask_image = None 
+        
+        # run inference pipeline
+        out = self.pipe(inputs, 
+                        image=image,             
+                        mask_image=mask_image,             
+                        num_inference_steps=num_inference_steps,
+                        guidance_scale=guidance_scale,
+                        num_images_per_prompt=1,
+                        negative_prompt=negative_prompt,
+                        height=height,
+                        width=width
+        )
+            
+        # return first generate PIL image
+        return out.images[0]
+    
+    # helper to decode input image
+    def decode_base64_image(self, image_string):
+        base64_image = base64.b64decode(image_string)
+        buffer = BytesIO(base64_image)
+        image = Image.open(buffer)
+        return image

test.py

@@ -1,7 +1,7 @@
 from handler import EndpointHandler
 
 # init handler
-my_handler = EndpointHandler(path=".")
+my_handler = EndpointHandler(path="./")
 
 # # prepare sample payload
 # non_holiday_payload = {"inputs": "I am quite excited how this will turn out", "date": "2022-08-08"}
@@ -15,3 +15,5 @@ my_handler = EndpointHandler(path=".")
 # print("non_holiday_pred", non_holiday_pred)
 # print("holiday_payload", holiday_payload)
 
+data = {"inputs": "Hello"}
+output = my_handler(data)