Upload 13 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/My_Love_2.jpg filter=lfs diff=lfs merge=lfs -text
+examples/My_Love.jpg filter=lfs diff=lfs merge=lfs -text
+examples/My_MiSheng.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,19 @@
+---
+title: BiRefNet Demo
+emoji: 🐠
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 4.38.1
+app_file: app.py
+pinned: false
+license: mit
+models:
+  - ZhengPeng7/BiRefNet
+  - ZhengPeng7/BiRefNet-portrait
+preload_from_hub:
+  - ZhengPeng7/BiRefNet
+  - ZhengPeng7/BiRefNet-portrait
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,228 @@
+import os
+import cv2
+import numpy as np
+import torch
+import gradio as gr
+import spaces
+
+from glob import glob
+from typing import Tuple
+
+from PIL import Image
+from gradio_imageslider import ImageSlider
+from transformers import AutoModelForImageSegmentation
+from torchvision import transforms
+
+import requests
+from io import BytesIO
+import zipfile
+
+
+torch.set_float32_matmul_precision('high')
+torch.jit.script = lambda f: f
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+### image_proc.py
+def refine_foreground(image, mask, r=90):
+    if mask.size != image.size:
+        mask = mask.resize(image.size)
+    image = np.array(image) / 255.0
+    mask = np.array(mask) / 255.0
+    estimated_foreground = FB_blur_fusion_foreground_estimator_2(image, mask, r=r)
+    image_masked = Image.fromarray((estimated_foreground * 255.0).astype(np.uint8))
+    return image_masked
+
+
+def FB_blur_fusion_foreground_estimator_2(image, alpha, r=90):
+    # Thanks to the source: https://github.com/Photoroom/fast-foreground-estimation
+    alpha = alpha[:, :, None]
+    F, blur_B = FB_blur_fusion_foreground_estimator(
+        image, image, image, alpha, r)
+    return FB_blur_fusion_foreground_estimator(image, F, blur_B, alpha, r=6)[0]
+
+
+def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
+    if isinstance(image, Image.Image):
+        image = np.array(image) / 255.0
+    blurred_alpha = cv2.blur(alpha, (r, r))[:, :, None]
+
+    blurred_FA = cv2.blur(F * alpha, (r, r))
+    blurred_F = blurred_FA / (blurred_alpha + 1e-5)
+
+    blurred_B1A = cv2.blur(B * (1 - alpha), (r, r))
+    blurred_B = blurred_B1A / ((1 - blurred_alpha) + 1e-5)
+    F = blurred_F + alpha * \
+        (image - alpha * blurred_F - (1 - alpha) * blurred_B)
+    F = np.clip(F, 0, 1)
+    return F, blurred_B
+
+
+class ImagePreprocessor():
+    def __init__(self, resolution: Tuple[int, int] = (1024, 1024)) -> None:
+        self.transform_image = transforms.Compose([
+            transforms.Resize(resolution),
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+    def proc(self, image: Image.Image) -> torch.Tensor:
+        image = self.transform_image(image)
+        return image
+
+
+usage_to_weights_file = {
+    'General': 'BiRefNet',
+    'General-Lite': 'BiRefNet_lite',
+    'General-Lite-2K': 'BiRefNet_lite-2K',
+    'Matting': 'BiRefNet-matting',
+    'Portrait': 'BiRefNet-portrait',
+    'DIS': 'BiRefNet-DIS5K',
+    'HRSOD': 'BiRefNet-HRSOD',
+    'COD': 'BiRefNet-COD',
+    'DIS-TR_TEs': 'BiRefNet-DIS5K-TR_TEs',
+    'General-legacy': 'BiRefNet-legacy'
+}
+
+birefnet = AutoModelForImageSegmentation.from_pretrained('/'.join(('zhengpeng7', usage_to_weights_file['General'])), trust_remote_code=True)
+birefnet.to(device)
+birefnet.eval()
+
+
+@spaces.GPU
+def predict(images, resolution, weights_file):
+    assert (images is not None), 'AssertionError: images cannot be None.'
+
+    global birefnet
+    # Load BiRefNet with chosen weights
+    _weights_file = '/'.join(('zhengpeng7', usage_to_weights_file[weights_file] if weights_file is not None else usage_to_weights_file['General']))
+    print('Using weights: {}.'.format(_weights_file))
+    birefnet = AutoModelForImageSegmentation.from_pretrained(_weights_file, trust_remote_code=True)
+    birefnet.to(device)
+    birefnet.eval()
+
+    try:
+        resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
+    except:
+        resolution = (1024, 1024) if weights_file not in ['General-Lite-2K'] else (2560, 1440)
+        print('Invalid resolution input. Automatically changed to 1024x1024 or 2K.')
+
+    if isinstance(images, list):
+        # For tab_batch
+        save_paths = []
+        save_dir = 'preds-BiRefNet'
+        if not os.path.exists(save_dir):
+            os.makedirs(save_dir)
+        tab_is_batch = True
+    else:
+        images = [images]
+        tab_is_batch = False
+
+    for idx_image, image_src in enumerate(images):
+        if isinstance(image_src, str):
+            if os.path.isfile(image_src):
+                image_ori = Image.open(image_src)
+            else:
+                response = requests.get(image_src)
+                image_data = BytesIO(response.content)
+                image_ori = Image.open(image_data)
+        else:
+            image_ori = Image.fromarray(image_src)
+
+        image = image_ori.convert('RGB')
+        # Preprocess the image
+        image_preprocessor = ImagePreprocessor(resolution=tuple(resolution))
+        image_proc = image_preprocessor.proc(image)
+        image_proc = image_proc.unsqueeze(0)
+
+        # Prediction
+        with torch.no_grad():
+            preds = birefnet(image_proc.to(device))[-1].sigmoid().cpu()
+        pred = preds[0].squeeze()
+
+        # Show Results
+        pred_pil = transforms.ToPILImage()(pred)
+        image_masked = refine_foreground(image, pred_pil)
+        image_masked.putalpha(pred_pil.resize(image.size))
+
+        torch.cuda.empty_cache()
+
+        if tab_is_batch:
+            save_file_path = os.path.join(save_dir, "{}.png".format(os.path.splitext(os.path.basename(image_src))[0]))
+            image_masked.save(save_file_path)
+            save_paths.append(save_file_path)
+
+    if tab_is_batch:
+        zip_file_path = os.path.join(save_dir, "{}.zip".format(save_dir))
+        with zipfile.ZipFile(zip_file_path, 'w') as zipf:
+            for file in save_paths:
+                zipf.write(file, os.path.basename(file))
+        return save_paths, zip_file_path
+    else:
+        return (image_masked, image_ori)
+
+
+examples = [[_] for _ in glob('examples/*')][:]
+# Add the option of resolution in a text box.
+for idx_example, example in enumerate(examples):
+    examples[idx_example].append('1024x1024')
+examples.append(examples[-1].copy())
+examples[-1][1] = '512x512'
+
+examples_url = [
+    ['https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg'],
+]
+for idx_example_url, example_url in enumerate(examples_url):
+    examples_url[idx_example_url].append('1024x1024')
+
+descriptions = ('Upload a picture, our model will extract a highly accurate segmentation of the subject in it.\n)'
+                 ' The resolution used in our training was `1024x1024`, thus the suggested resolution to obtain good results!\n'
+                 ' Our codes can be found at https://github.com/ZhengPeng7/BiRefNet.\n'
+                 ' We also maintain the HF model of BiRefNet at https://huggingface.co/ZhengPeng7/BiRefNet for easier access.')
+
+tab_image = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Image(label='Upload an image'),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=ImageSlider(label="BiRefNet's prediction", type="pil"),
+    examples=examples,
+    api_name="image",
+    description=descriptions,
+)
+
+tab_text = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Paste an image URL"),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=ImageSlider(label="BiRefNet's prediction", type="pil"),
+    examples=examples_url,
+    api_name="text",
+    description=descriptions+'\nTab-URL is partially modified from https://huggingface.co/spaces/not-lain/background-removal, thanks to this great work!',
+)
+
+tab_batch = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.File(label="Upload multiple images", type="filepath", file_count="multiple"),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=[gr.Gallery(label="BiRefNet's predictions"), gr.File(label="Download masked images.")],
+    api_name="batch",
+    description=descriptions+'\nTab-batch is partially modified from https://huggingface.co/spaces/NegiTurkey/Multi_Birefnetfor_Background_Removal, thanks to this great work!',
+)
+
+demo = gr.TabbedInterface(
+    [tab_image, tab_text, tab_batch],
+    ['image', 'text', 'batch'],
+    title="BiRefNet demo for subject extraction (general / matting / salient / camouflaged / portrait).",
+)
+
+if __name__ == "__main__":
+    demo.launch(debug=True)

app_local.py

@@ -0,0 +1,228 @@
+import os
+import cv2
+import numpy as np
+import torch
+import gradio as gr
+# import spaces
+
+from glob import glob
+from typing import Tuple
+
+from PIL import Image
+# from gradio_imageslider import ImageSlider
+from transformers import AutoModelForImageSegmentation
+from torchvision import transforms
+
+import requests
+from io import BytesIO
+import zipfile
+
+
+torch.set_float32_matmul_precision('high')
+# torch.jit.script = lambda f: f
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+### image_proc.py
+def refine_foreground(image, mask, r=90):
+    if mask.size != image.size:
+        mask = mask.resize(image.size)
+    image = np.array(image) / 255.0
+    mask = np.array(mask) / 255.0
+    estimated_foreground = FB_blur_fusion_foreground_estimator_2(image, mask, r=r)
+    image_masked = Image.fromarray((estimated_foreground * 255.0).astype(np.uint8))
+    return image_masked
+
+
+def FB_blur_fusion_foreground_estimator_2(image, alpha, r=90):
+    # Thanks to the source: https://github.com/Photoroom/fast-foreground-estimation
+    alpha = alpha[:, :, None]
+    F, blur_B = FB_blur_fusion_foreground_estimator(
+        image, image, image, alpha, r)
+    return FB_blur_fusion_foreground_estimator(image, F, blur_B, alpha, r=6)[0]
+
+
+def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
+    if isinstance(image, Image.Image):
+        image = np.array(image) / 255.0
+    blurred_alpha = cv2.blur(alpha, (r, r))[:, :, None]
+
+    blurred_FA = cv2.blur(F * alpha, (r, r))
+    blurred_F = blurred_FA / (blurred_alpha + 1e-5)
+
+    blurred_B1A = cv2.blur(B * (1 - alpha), (r, r))
+    blurred_B = blurred_B1A / ((1 - blurred_alpha) + 1e-5)
+    F = blurred_F + alpha * \
+        (image - alpha * blurred_F - (1 - alpha) * blurred_B)
+    F = np.clip(F, 0, 1)
+    return F, blurred_B
+
+
+class ImagePreprocessor():
+    def __init__(self, resolution: Tuple[int, int] = (1024, 1024)) -> None:
+        self.transform_image = transforms.Compose([
+            transforms.Resize(resolution),
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+    def proc(self, image: Image.Image) -> torch.Tensor:
+        image = self.transform_image(image)
+        return image
+
+
+usage_to_weights_file = {
+    'General': 'BiRefNet',
+    'General-Lite': 'BiRefNet_lite',
+    'General-Lite-2K': 'BiRefNet_lite-2K',
+    'Matting': 'BiRefNet-matting',
+    'Portrait': 'BiRefNet-portrait',
+    'DIS': 'BiRefNet-DIS5K',
+    'HRSOD': 'BiRefNet-HRSOD',
+    'COD': 'BiRefNet-COD',
+    'DIS-TR_TEs': 'BiRefNet-DIS5K-TR_TEs',
+    'General-legacy': 'BiRefNet-legacy'
+}
+
+birefnet = AutoModelForImageSegmentation.from_pretrained('/'.join(('zhengpeng7', usage_to_weights_file['General'])), trust_remote_code=True)
+birefnet.to(device)
+birefnet.eval()
+
+
+# @spaces.GPU
+def predict(images, resolution, weights_file):
+    assert (images is not None), 'AssertionError: images cannot be None.'
+
+    global birefnet
+    # Load BiRefNet with chosen weights
+    _weights_file = '/'.join(('zhengpeng7', usage_to_weights_file[weights_file] if weights_file is not None else usage_to_weights_file['General']))
+    print('Using weights: {}.'.format(_weights_file))
+    birefnet = AutoModelForImageSegmentation.from_pretrained(_weights_file, trust_remote_code=True)
+    birefnet.to(device)
+    birefnet.eval()
+
+    try:
+        resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
+    except:
+        resolution = (1024, 1024) if weights_file not in ['General-Lite-2K'] else (2560, 1440)
+        print('Invalid resolution input. Automatically changed to 1024x1024 or 2K.')
+
+    if isinstance(images, list):
+        # For tab_batch
+        save_paths = []
+        save_dir = 'preds-BiRefNet'
+        if not os.path.exists(save_dir):
+            os.makedirs(save_dir)
+        tab_is_batch = True
+    else:
+        images = [images]
+        tab_is_batch = False
+
+    for idx_image, image_src in enumerate(images):
+        if isinstance(image_src, str):
+            if os.path.isfile(image_src):
+                image_ori = Image.open(image_src)
+            else:
+                response = requests.get(image_src)
+                image_data = BytesIO(response.content)
+                image_ori = Image.open(image_data)
+        else:
+            image_ori = Image.fromarray(image_src)
+
+        image = image_ori.convert('RGB')
+        # Preprocess the image
+        image_preprocessor = ImagePreprocessor(resolution=tuple(resolution))
+        image_proc = image_preprocessor.proc(image)
+        image_proc = image_proc.unsqueeze(0)
+
+        # Prediction
+        with torch.no_grad():
+            preds = birefnet(image_proc.to(device))[-1].sigmoid().cpu()
+        pred = preds[0].squeeze()
+
+        # Show Results
+        pred_pil = transforms.ToPILImage()(pred)
+        image_masked = refine_foreground(image, pred_pil)
+        image_masked.putalpha(pred_pil.resize(image.size))
+
+        torch.cuda.empty_cache()
+
+        if tab_is_batch:
+            save_file_path = os.path.join(save_dir, "{}.png".format(os.path.splitext(os.path.basename(image_src))[0]))
+            image_masked.save(save_file_path)
+            save_paths.append(save_file_path)
+
+    if tab_is_batch:
+        zip_file_path = os.path.join(save_dir, "{}.zip".format(save_dir))
+        with zipfile.ZipFile(zip_file_path, 'w') as zipf:
+            for file in save_paths:
+                zipf.write(file, os.path.basename(file))
+        return save_paths, zip_file_path
+    else:
+        return (image_masked, image_ori)[0]
+
+
+examples = [[_] for _ in glob('examples/*')][:]
+# Add the option of resolution in a text box.
+for idx_example, example in enumerate(examples):
+    examples[idx_example].append('1024x1024')
+examples.append(examples[-1].copy())
+examples[-1][1] = '512x512'
+
+examples_url = [
+    ['https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg'],
+]
+for idx_example_url, example_url in enumerate(examples_url):
+    examples_url[idx_example_url].append('1024x1024')
+
+descriptions = ('Upload a picture, our model will extract a highly accurate segmentation of the subject in it.\n)'
+                 ' The resolution used in our training was `1024x1024`, thus the suggested resolution to obtain good results!\n'
+                 ' Our codes can be found at https://github.com/ZhengPeng7/BiRefNet.\n'
+                 ' We also maintain the HF model of BiRefNet at https://huggingface.co/ZhengPeng7/BiRefNet for easier access.')
+
+tab_image = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Image(label='Upload an image'),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=gr.Image(label="BiRefNet's prediction", type="pil", format='png'),
+    examples=examples,
+    api_name="image",
+    description=descriptions,
+)
+
+tab_text = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Paste an image URL"),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=gr.Image(label="BiRefNet's prediction", type="pil", format='png'),
+    examples=examples_url,
+    api_name="text",
+    description=descriptions+'\nTab-URL is partially modified from https://huggingface.co/spaces/not-lain/background-removal, thanks to this great work!',
+)
+
+tab_batch = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.File(label="Upload multiple images", type="filepath", file_count="multiple"),
+        gr.Textbox(lines=1, placeholder="Type the resolution (`WxH`) you want, e.g., `1024x1024`.", label="Resolution"),
+        gr.Radio(list(usage_to_weights_file.keys()), value='General', label="Weights", info="Choose the weights you want.")
+    ],
+    outputs=[gr.Gallery(label="BiRefNet's predictions"), gr.File(label="Download masked images.")],
+    api_name="batch",
+    description=descriptions+'\nTab-batch is partially modified from https://huggingface.co/spaces/NegiTurkey/Multi_Birefnetfor_Background_Removal, thanks to this great work!',
+)
+
+demo = gr.TabbedInterface(
+    [tab_image, tab_text, tab_batch],
+    ['image', 'text', 'batch'],
+    title="BiRefNet demo for subject extraction (general / matting / salient / camouflaged / portrait).",
+)
+
+if __name__ == "__main__":
+    demo.launch(debug=True)

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

gitignore

@@ -0,0 +1,5 @@
+flagged/
+
+__pycache__/
+
+.DS_Store

requirements (1).txt

@@ -0,0 +1,12 @@
+torch==2.0.1
+torchvision==0.15.2
+opencv-python==4.9.0.80
+tqdm==4.66.2
+timm==0.9.16
+prettytable==3.10.0
+scipy==1.12.0
+scikit-image==0.22.0
+kornia==0.7.1
+gradio_imageslider==0.0.18
+transformers==4.42.4
+huggingface_hub==0.23.4