bugfix

app.py

@@ -22,6 +22,7 @@ from diffusers.utils import load_image
 import json
 from preprocessor import Preprocessor
 from diffusers.pipelines.flux.pipeline_flux_controlnet_inpaint import FluxControlNetInpaintPipeline
+from diffusers.models.controlnet_flux import FluxControlNetModel
 
 HF_TOKEN = os.environ.get("HF_TOKEN")
 

cv_utils.py

@@ -0,0 +1,18 @@
+import cv2
+import numpy as np
+
+MAX_IMAGE_SIZE = 512
+
+def resize_image(input_image, resolution=MAX_IMAGE_SIZE, interpolation=None):
+    H, W, C = input_image.shape
+    H = float(H)
+    W = float(W)
+    k = float(resolution) / max(H, W)
+    H *= k
+    W *= k
+    H = int(np.round(H / 64.0)) * 64
+    W = int(np.round(W / 64.0)) * 64
+    if interpolation is None:
+        interpolation = cv2.INTER_LANCZOS4 if k > 1 else cv2.INTER_AREA
+    img = cv2.resize(input_image, (W, H), interpolation=interpolation)
+    return img

depth_estimator.py

@@ -0,0 +1,14 @@
+import numpy as np
+import PIL.Image
+from controlnet_aux.util import HWC3
+from transformers import pipeline
+
+from cv_utils import resize_image
+
+
+class DepthEstimator:
+    def __init__(self):
+        self.model = pipeline("depth-estimation")
+
+    def __call__(self, image: np.ndarray, **kwargs) -> PIL.Image.Image:
+        return image

image_segmentor.py

@@ -0,0 +1,34 @@
+import cv2
+import numpy as np
+import PIL.Image
+import torch
+from controlnet_aux.util import HWC3, ade_palette
+from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
+
+from cv_utils import resize_image
+
+
+class ImageSegmentor:
+    
+    def __init__(self):
+        self.image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
+        self.image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
+
+    @torch.no_grad()
+    def __call__(self, image: np.ndarray, **kwargs) -> PIL.Image.Image:
+        detect_resolution = kwargs.pop("detect_resolution", 512)
+        image_resolution = kwargs.pop("image_resolution", 512)
+        image = HWC3(image)
+        image = resize_image(image, resolution=detect_resolution)
+        image = PIL.Image.fromarray(image)
+
+        pixel_values = self.image_processor(image, return_tensors="pt").pixel_values
+        outputs = self.image_segmentor(pixel_values)
+        seg = self.image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+        color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8)
+        for label, color in enumerate(ade_palette()):
+            color_seg[seg == label, :] = color
+        color_seg = color_seg.astype(np.uint8)
+
+        color_seg = resize_image(color_seg, resolution=image_resolution, interpolation=cv2.INTER_NEAREST)
+        return PIL.Image.fromarray(color_seg)