Update app.py

app.py

@@ -8,33 +8,18 @@ from PIL import Image
 import cv2
 
 import torch
-from diffusers import StableDiffusion3Pipeline
-from diffusers.models.controlnet_sd3 import ControlNetSD3Model
-from diffusers.utils.torch_utils import randn_tensor
-from diffusers.utils import load_image
-
-# Clone the specific branch
-subprocess.run(["git", "clone", "-b", "sd3_control", "https://github.com/instantX-research/diffusers_sd3_control.git"])
-
-# Change directory to the cloned repository and install it
-os.chdir('diffusers_sd3_control')
-subprocess.run(["pip", "install", "-e", "."])
-
-# Add the path to the examples directory
-sys.path.append(os.path.abspath('./examples/community'))
-
-# Import the required pipeline
-from pipeline_stable_diffusion_3_controlnet import StableDiffusion3CommonPipeline
-
 
+from diffusers import StableDiffusion3ControlNetPipeline
+from diffusers.models import SD3ControlNetModel, SD3MultiControlNetModel
+from diffusers.utils import load_image
 
 # load pipeline
-base_model = 'stabilityai/stable-diffusion-3-medium-diffusers'
-pipe = StableDiffusion3CommonPipeline.from_pretrained(
-    base_model, 
-    controlnet_list=['InstantX/SD3-Controlnet-Canny'],
+controlnet = SD3ControlNetModel.from_pretrained("InstantX/SD3-Controlnet-Canny")
+pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-3-medium-diffusers",
+    controlnet=controlnet
 )
-pipe.to('cuda:0', torch.float16)
+pipe.to("cuda", torch.float16)
 
 def resize_image(input_path, output_path, target_height):
     # Open the input image
@@ -68,21 +53,13 @@ def infer(image_in, prompt, inference_steps, guidance_scale, control_weight, pro
     image_to_canny = np.concatenate([image_to_canny, image_to_canny, image_to_canny], axis=2)
     image_to_canny = Image.fromarray(image_to_canny)
     
-    # controlnet config
-    controlnet_conditioning = [
-        dict(
-            control_index=0,
-            control_image=image_to_canny,
-            control_weight=control_weight,
-            control_pooled_projections='zeros'
-        )
-    ]
     
     # infer
     image = pipe(
         prompt=prompt,
         negative_prompt=n_prompt,
-        controlnet_conditioning=controlnet_conditioning,
+        control_image=image_to_canny, 
+        controlnet_conditioning_scale=control_weigth,
         num_inference_steps=inference_steps,
         guidance_scale=guidance_scale,
     ).images[0]