Update app.py

app.py

@@ -1,9 +1,12 @@
 import gradio as gr
 import numpy as np
+import PIL.Image
 from PIL import Image
 import random
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
 from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
+from diffusers.utils import load_image
+
 import cv2
 import torch
 import spaces
@@ -48,34 +51,31 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1216
 
 @spaces.GPU
-def infer(image: Image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps) -> Image:
+def infer(image: PIL.Image.Image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps) -> PIL.Image.Image:
 
-    width, height = image.size
+    width, height  = image['composite'].size
     ratio = np.sqrt(1024. * 1024. / (width * height))
     new_width, new_height = int(width * ratio), int(height * ratio)
-    image = image.resize((new_width, new_height))
+    image = image['composite'].resize((new_width, new_height))
 
+    print(image)
+    
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
 
-    controlnet_img = np.array(image)
-    controlnet_img = nms(controlnet_img, 127, 3)
-    controlnet_img = cv2.GaussianBlur(controlnet_img, (0, 0), 3)
-
-    random_val = int(round(random.uniform(0.01, 0.10), 2) * 255)
-    controlnet_img[controlnet_img > random_val] = 255
-    controlnet_img[controlnet_img < 255] = 0
-    image = Image.fromarray(controlnet_img)
+    controlnet_img = image
 
     generator = torch.Generator().manual_seed(seed)
 
     output_image = pipe(
         prompt=prompt + ", masterpiece, best quality, very aesthetic, absurdres",
         negative_prompt=negative_prompt,
+        image=image,
+        controlnet_conditioning_scale=1.0,
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
+        width=new_width,
+        height=new_height,
         generator=generator
     ).images[0]
 
@@ -135,7 +135,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=832,
+                    value=1024,#832,
                 )
 
                 height = gr.Slider(
@@ -143,7 +143,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1216,
+                    value=1024,#1216,
                 )
 
             with gr.Row():
@@ -163,7 +163,7 @@ with gr.Blocks(css=css) as demo:
                     value=28,
                 )
 
-    run_button.click(
+    run_button.click(lambda x: None, inputs=None, outputs=image_slider).then(
         fn=infer,
         inputs=[image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
         outputs=[result]