Update handler.py

handler.py

@@ -24,7 +24,7 @@ class EndpointHandler():
         # )
         # self.smooth_pipe.to("cuda")
 
-        """
+        
         self.controlnet = ControlNetModel.from_pretrained(
             "lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16
         )
@@ -36,8 +36,8 @@ class EndpointHandler():
         self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.enable_model_cpu_offload()
         self.pipe.enable_xformers_memory_efficient_attention()
+        
         """
-
         # load StableDiffusionInpaintPipeline pipeline
         self.pipe = AutoPipelineForInpainting.from_pretrained(
             "runwayml/stable-diffusion-inpainting",
@@ -45,7 +45,7 @@ class EndpointHandler():
             torch_dtype=torch.float16,
         )
         # use DPMSolverMultistepScheduler
-        self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(self.pipe.scheduler.config)
+        self.pipe.scheduler = DPMSolverMultistepScheduler.from_config(self.pipe.scheduler.config)
 
         self.pipe.enable_model_cpu_offload()
 
@@ -63,6 +63,7 @@ class EndpointHandler():
         self.pipe3 = AutoPipelineForImage2Image.from_pipe(self.pipe2)
         #self.pipe3.enable_model_cpu_offload()
         self.pipe3.enable_xformers_memory_efficient_attention()
+        """
 
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
@@ -114,7 +115,7 @@ class EndpointHandler():
         """
 
         #pipe = AutoPipelineForInpainting.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", torch_dtype=torch.float16, variant="fp16").to("cuda")
-        
+        """
         # run inference pipeline
         out = self.pipe(prompt=prompt, negative_prompt=negative_prompt, image=image, mask_image=mask_image, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale)
 
@@ -123,7 +124,7 @@ class EndpointHandler():
         image = out.images[0].resize((1024, 1024))
 
         print("image resizing successful!")
-        """
+        
         image = self.pipe2(
             prompt=prompt,
             negative_prompt=negative_prompt,
@@ -146,12 +147,13 @@ class EndpointHandler():
         ).images[0]
 
         print("3rd pipeline part successful!")
-        """
+        
             
         # return first generate PIL image
         return image
-        
         """
+        
+        
         control_image = self.make_inpaint_condition(image, mask_image)
 
         # generate image
@@ -168,7 +170,7 @@ class EndpointHandler():
         ).images[0]
 
         return image
-        """
+        
     
     # helper to decode input image
     def decode_base64_image(self, image_string):