refactor: add venv locally and num_of_images parameter and return list of images instead of string

.gitignore

@@ -0,0 +1 @@
+/.venv

handler.py

@@ -78,12 +78,16 @@ class EndpointHandler():
         """
         prompt = data.pop("inputs", None)
         image = data.pop("image", None)
+        num_of_images = data.pop("numOfImages", None)
         controlnet_type = data.pop("controlnet_type", None)
         
         # Check if neither prompt nor image is provided
         if prompt is None and image is None:
             return {"error": "Please provide a prompt and base64 encoded image."}
         
+        if num_of_images is None:
+            num_of_images = 1
+        
         # Check if a new controlnet is provided
         if controlnet_type is not None and controlnet_type != self.control_type:
             print(f"changing controlnet from {self.control_type} to {controlnet_type} using {CONTROLNET_MAPPING[controlnet_type]['model_id']} model")
@@ -112,7 +116,7 @@ class EndpointHandler():
             image=control_image,
             num_inference_steps=num_inference_steps, 
             guidance_scale=guidance_scale,
-            num_images_per_prompt=1,
+            num_images_per_prompt=num_of_images,
             height=height,
             width=width,
             controlnet_conditioning_scale=controlnet_conditioning_scale,
@@ -120,8 +124,8 @@ class EndpointHandler():
         )
 
         
-        # return first generate PIL image
-        return out.images[0]
+        # return the list of generated images
+        return out.images
     
     # helper to decode input image
     def decode_base64_image(self, image_string):