make it load data_uris

handler.py

@@ -2,7 +2,7 @@ from typing import  Dict, List, Any
 import torch
 from PIL import Image
 from io import BytesIO
-import requests
+from urllib import request
 from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DDIMScheduler
 
 # set device
@@ -36,33 +36,38 @@ class EndpointHandler():
         prompt = data.pop("inputs", data)
         url = data.pop("url", data)
 
-        response = requests.get(url)
-        init_image = Image.open(BytesIO(response.content)).convert("RGB")
-        init_image.thumbnail((512, 512))
+        with request.urlopen(data_uri) as response:
+            data = response.read()
+            init_image = Image.open(BytesIO(data)).convert("RGB")
+            init_image = Image.open(url)
+            init_image.thumbnail((512, 512))
 
 
-        params = data.pop("parameters", data)
+            params = data.pop("parameters", data)
 
-        # hyperparamters
-        num_inference_steps = params.pop("num_inference_steps", 25)
-        guidance_scale = params.pop("guidance_scale", 7.5)
-        negative_prompt = params.pop("negative_prompt", None)
-        height = params.pop("height", None)
-        width = params.pop("width", None)
-        manual_seed = params.pop("manual_seed", -1)
+            # hyperparamters
+            num_inference_steps = params.pop("num_inference_steps", 25)
+            guidance_scale = params.pop("guidance_scale", 7.5)
+            negative_prompt = params.pop("negative_prompt", None)
+            prompt = params.pop("prompt", None)
+            height = params.pop("height", None)
+            width = params.pop("width", None)
+            manual_seed = params.pop("manual_seed", -1)
 
-        out = None
+            out = None
 
-        generator = torch.Generator(device='cuda')
-        generator.manual_seed(manual_seed)
-        # run img2img pipeline
-        out = self.imgPipe(prompt,
-                    image=init_image,
-                    num_inference_steps=num_inference_steps,
-                    guidance_scale=guidance_scale,
-                    num_images_per_prompt=1,
-                    negative_prompt=negative_prompt
-        )
+            generator = torch.Generator(device='cuda')
+            generator.manual_seed(manual_seed)
+            # run img2img pipeline
+            out = self.imgPipe(prompt,
+                        image=init_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 generated PIL image
-        return out.images[0]
+            # return first generated PIL image
+            return out.images[0]