up 8

app.py

@@ -3,7 +3,7 @@ import io
 from PIL import Image
 import numpy as np
 
-import config
+# from config import setResoluton
 from models import make_image_controlnet, make_inpainting
 from preprocessing import get_mask
 
@@ -24,30 +24,35 @@ def predict(input_img1,
             resolution
             ):
 
+
+
     print("predict")
     # bla bla
     # input_img1 = Image.fromarray(input_img1)
     # input_img2 = Image.fromarray(input_img2)
 
-    config.setResoluton(resolution)
+    # setResoluton(resolution)
+    HEIGHT = resolution
+    WIDTH = resolution
+    # WIDTH = resolution
+    # HEIGHT = resolution
 
-    input_img1 = input_img1.resize((config.WIDTH, config.HEIGHT))
-    input_img2 = input_img2.resize((config.WIDTH, config.HEIGHT))
+    input_img1 = input_img1.resize((resolution, resolution))
+    input_img2 = input_img2.resize((resolution, resolution))
 
     canvas_mask = np.array(input_img2)
     mask = get_mask(canvas_mask)
 
     print(input_img1, mask, positive_prompt, negative_prompt)
 
-    retList=[]
-    for x in range(num_of_images):
-        result_image = make_inpainting(positive_prompt=positive_prompt,
-                                   image=input_img1,
-                                   mask_image=mask,
-                                   negative_prompt=negative_prompt,
-                                   )
-        retList.append(result_image)
-
+    retList=  make_inpainting(positive_prompt=positive_prompt,
+                               image=input_img1,
+                               mask_image=mask,
+                               negative_prompt=negative_prompt,
+                               num_of_images=num_of_images,
+                               resolution=resolution
+                               )
+    # add the rest up to 10
     while (len(retList)<10):
         retList.append(None)
 

config.py

@@ -3,14 +3,14 @@ from palette import COLOR_MAPPING_, COLOR_MAPPING
 
 # HEIGHT = 1024
 # WIDTH = 1024
-HEIGHT = 512
-WIDTH = 512
+# HEIGHT = 512
+# WIDTH = 512
 #
 
-def setResoluton(res):
-    global HEIGHT, WIDTH
-    HEIGHT = res
-    WIDTH = res
+# def setResoluton(res):
+#     global HEIGHT, WIDTH
+#     HEIGHT = res
+#     WIDTH = res
 
 def to_rgb(color: str) -> tuple:
     """Convert hex color to rgb.

models.py

@@ -12,7 +12,7 @@ from PIL import ImageFilter
 
 from diffusers import ControlNetModel, UniPCMultistepScheduler
 
-from config import WIDTH, HEIGHT
+# from config import WIDTH, HEIGHT
 from palette import ade_palette
 from stable_diffusion_controlnet_inpaint_img2img import StableDiffusionControlNetInpaintImg2ImgPipeline
 from helpers import flush, postprocess_image_masking, convolution
@@ -70,7 +70,9 @@ def make_inpainting(positive_prompt: str,
                     image: Image,
                     mask_image: np.ndarray,
                     negative_prompt: str = "",
-                    rezolution:int=512) -> List[Image.Image]:
+                    num_of_images: int = 1,
+                    resolution:int = 512) -> List[Image.Image]:
+
     """Method to make inpainting
     Args:
         positive_prompt (str): positive prompt string
@@ -85,17 +87,20 @@ def make_inpainting(positive_prompt: str,
     mask_image_postproc = convolution(mask_image)
 
     flush()
-    st.success(f"{pipe.queue_size} images in the queue, can take up to {(pipe.queue_size+1) * 10} seconds")
-    resp = pipe(image=image,
-                    mask_image=mask_image,
-                    prompt=positive_prompt,
-                    negative_prompt=negative_prompt,
-                    num_inference_steps=50,
-                    height=rezolution,
-                    width=rezolution,
-                    )
-    print("RESP !!!!",resp)
-    generated_image = resp.images[0]
-    generated_image = postprocess_image_masking(generated_image, image, mask_image_postproc)
+    retList=[]
+    for x in range(num_of_images):
+        st.success(f"{pipe.queue_size} images in the queue, can take up to {(pipe.queue_size+1) * 10} seconds")
+        resp = pipe(image=image,
+                        mask_image=mask_image,
+                        prompt=positive_prompt,
+                        negative_prompt=negative_prompt,
+                        num_inference_steps=50,
+                        height=resolution,
+                        width=resolution,
+                        )
+        print("RESP !!!!",resp)
+        generated_image = resp.images[0]
+        generated_image = postprocess_image_masking(generated_image, image, mask_image_postproc)
+        retList.append(generated_image)
 
-    return generated_image
+    return retList

pipelines.py

@@ -15,7 +15,7 @@ from PIL import ImageFilter
 from diffusers import ControlNetModel, UniPCMultistepScheduler
 from diffusers import StableDiffusionInpaintPipeline
 
-from config import WIDTH, HEIGHT
+# from config import WIDTH, HEIGHT
 from stable_diffusion_controlnet_inpaint_img2img import StableDiffusionControlNetInpaintImg2ImgPipeline
 from helpers import flush
 

preprocessing.py

@@ -6,8 +6,7 @@ import numpy as np
 from PIL import Image, ImageFilter
 import streamlit as st
 
-import config
-
+from config import COLOR_RGB
 # from enhance_config import ENHANCE_SETTINGS
 
 LOGGING = logging.getLogger(__name__)
@@ -36,7 +35,7 @@ def preprocess_seg_mask(canvas_seg, real_seg: Image.Image = None) -> Tuple[np.nd
     unique_colors = [color for color in unique_colors if np.sum(
         np.all(image_seg == color, axis=-1)) > 100]
 
-    unique_colors_exact = [color for color in unique_colors if color in config.COLOR_RGB]
+    unique_colors_exact = [color for color in unique_colors if color in COLOR_RGB]
 
     if real_seg is not None:
         overlay_seg = np.array(real_seg)
@@ -68,6 +67,7 @@ def get_mask(image_mask: np.ndarray) -> np.ndarray:
 
 
 def get_image() -> np.ndarray:
+
     """Get the image from the session state.
     Returns:
         np.ndarray: image
@@ -75,9 +75,9 @@ def get_image() -> np.ndarray:
     if 'initial_image' in st.session_state and st.session_state['initial_image'] is not None:
         initial_image = st.session_state['initial_image']
         if isinstance(initial_image, Image.Image):
-            return np.array(initial_image.resize((config.WIDTH, config.HEIGHT)))
+            return np.array(initial_image.resize((WIDTH, HEIGHT)))
         else:
-            return np.array(Image.fromarray(initial_image).resize((config.WIDTH, config.HEIGHT)))
+            return np.array(Image.fromarray(initial_image).resize((WIDTH, HEIGHT)))
     else:
         return None