a

handler.py

@@ -0,0 +1,65 @@
+from typing import Dict, List, Any
+from transformers import pipeline
+from diffusers import AutoPipelineForText2Image
+import torch
+import base64
+from io import BytesIO
+from PIL import Image
+
+
+class EndpointHandler():
+    def __init__(self, path=""):        
+        self.pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
+        self.pipe.to("cuda")
+
+    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """
+       data args:
+            inputs (:obj: `str`)
+            date (:obj: `str`)
+       Return:
+            A :obj:`list` | `dict`: will be serialized and returned
+        """
+        # get inputs
+        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        
+        
+