upd

app.py

@@ -7,6 +7,8 @@ from io import BytesIO
 from rembg import remove
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 import torch
+from diffusers import UniPCMultistepScheduler
+
 
 def remove_background(input_image: Image.Image, to_grayscale: bool) -> Image.Image:
     output_image = remove(input_image)
@@ -27,20 +29,24 @@ def canny_image(image: Image.Image) -> Image.Image:
     return Image.fromarray(np_image)
 
 def process_image(input_image: Image.Image, to_grayscale: bool, prompt: str) -> Image.Image:
-    canny_output = canny_image(input_image)
+    output_image = remove_background(input_image, to_grayscale)
+    canny_output = canny_image(output_image)
 
     controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float32)
     pipe = StableDiffusionControlNetPipeline.from_pretrained(
         "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float32
     )
     pipe.enable_model_cpu_offload()
+    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+    pipe.enable_xformers_memory_efficient_attention()
+    
     generator = torch.manual_seed(2)
     output = pipe(
-        [prompt],
+        prompt,
         canny_output,
-        negative_prompt=["monochrome, lowres, bad anatomy, worst quality, low quality"],
+        negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
         generator=generator,
-        num_inference_steps=20,
+        num_inference_steps=2,
     )
 
     return output.images[0]