test 2

handler.py

@@ -6,6 +6,7 @@ from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 #from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, StableDiffusionSafetyChecker
 # import Safety Checker
 from diffusers.pipelines.stable_diffusion import StableDiffusionSafetyChecker
+from diffusers.pipelines.stable_diffusion import StableDiffusionPipeline
 
 import torch
 
@@ -75,15 +76,11 @@ class EndpointHandler():
                                                                       controlnet=self.controlnet, 
                                                                       torch_dtype=dtype,
                                                                       safety_checker=StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker", torch_dtype=dtype)).to("cuda")
+
+        self.pipe_without_controlnet = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=dtype).to(device.type)
+
         # Define Generator with seed
         self.generator = torch.Generator(device=device.type).manual_seed(3)
-        
-        targets = [self.pipe.vae, self.pipe.unet]
-        for target in targets:
-            for module in target.modules():
-                if isinstance(module, torch.nn.Conv2d):
-                    module.padding_mode = "circular"
-        
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         """
@@ -107,7 +104,12 @@ class EndpointHandler():
             self.pipe.controlnet = self.controlnet
         
         
-
+        targets = [self.pipe_without_controlnet.vae, self.pipe_without_controlnet.unet]
+        for target in targets:
+            for module in target.modules():
+                if isinstance(module, torch.nn.Conv2d):
+                    module.padding_mode = "circular"
+        
         # hyperparamters
         num_inference_steps = data.pop("num_inference_steps", 30)
         guidance_scale = data.pop("guidance_scale", 7.4)
@@ -127,17 +129,17 @@ class EndpointHandler():
         #control_image = CONTROLNET_MAPPING[self.control_type]["hinter"](image)
 
         # run inference pipeline
-        out = self.pipe(
+        out = self.pipe_without_controlnet(
             prompt=prompt, 
             negative_prompt=negative_prompt,
             #image=control_image,
-            image=image,
+            #image=image,
             num_inference_steps=num_inference_steps, 
             guidance_scale=guidance_scale,
             num_images_per_prompt=1,
             height=height,
             width=width,
-            controlnet_conditioning_scale=controlnet_conditioning_scale,
+            #controlnet_conditioning_scale=controlnet_conditioning_scale,
             generator=self.generator
         )