add rmbg

app.py

@@ -1,12 +1,48 @@
 import gradio as gr
 import spaces
 import torch
+from loadimg import load_img
+from torchvision import transforms
+from transformers import AutoModelForImageSegmentation
+
+torch.set_float32_matmul_precision(["high", "highest"][0])
+
+birefnet = AutoModelForImageSegmentation.from_pretrained(
+    "ZhengPeng7/BiRefNet", trust_remote_code=True
+)
+birefnet.to("cuda")
+
+transform_image = transforms.Compose(
+    [
+        transforms.Resize((1024, 1024)),
+        transforms.ToTensor(),
+        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+    ]
+)
 
-zero = torch.Tensor([0]).cuda()
 
 @spaces.GPU
-def greet(n):
-    return f"Hello {zero + n} Tensor"
+def rmbg(image):
+    image = load_img().convert("RGB")
+    image_size = image.size
+    input_images = transform_image(image).unsqueeze(0).to("cuda")
+    # Prediction
+    with torch.no_grad():
+        preds = birefnet(input_images)[-1].sigmoid().cpu()
+    pred = preds[0].squeeze()
+    pred_pil = transforms.ToPILImage()(pred)
+    mask = pred_pil.resize(image_size)
+    image.putalpha(mask)
+    return image
+
+
+rmbg_tab = gr.Interface(fn=rmbg, inputs=["text"], outputs=["image"], api_name="rmbg")
+
+demo = gr.TabbedInterface(
+    [rmbg_tab],
+    ["remove background"],
+    title="Background Removal",
+)
+
 
-demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
-demo.launch()
+demo.launch()

requirements

@@ -1,2 +1,14 @@
 spaces
-torch
+torch
+torchvision
+opencv-python
+tqdm
+timm
+prettytable
+scipy
+scikit-image
+kornia
+gradio_imageslider
+transformers
+huggingface_hub
+loadimg