chinese-support

MyPipe.py

@@ -50,9 +50,9 @@ class RMBGPipe(Pipeline):
     pil_im = Image.fromarray(result_image)
     if return_mask ==True : 
       return pil_im
+    no_bg_image = Image.new("RGBA", pil_im.size, (0,0,0,0))
     input_image = load_image(input_image)
-    no_bg_image = input_image.copy()
-    no_bg_image.putalpha(pil_im)
+    no_bg_image.paste(input_image, mask=pil_im)
     return no_bg_image
     
   # utilities functions

README.md

@@ -34,27 +34,16 @@ It is ideal where content safety, legally licensed datasets, and bias mitigation
 
 Developed by BRIA AI, RMBG v1.4 is available as a source-available model for non-commercial use. 
 
-
-To purchase a commercial license, simply click [Here](https://go.bria.ai/3D5EGp0).
-
-
 [CLICK HERE FOR A DEMO](https://huggingface.co/spaces/briaai/BRIA-RMBG-1.4)
-
-**NOTE** New RMBG version available! Check out [RMBG-2.0](https://huggingface.co/briaai/RMBG-2.0)
-
-Join our [Discord community](https://discord.gg/Nxe9YW9zHS) for more information, tutorials, tools, and to connect with other users!
-
-
 ![examples](t4.png)
 
-
 ### Model Description
 
 - **Developed by:** [BRIA AI](https://bria.ai/)
 - **Model type:** Background Removal 
 - **License:** [bria-rmbg-1.4](https://bria.ai/bria-huggingface-model-license-agreement/)
   - The model is released under a Creative Commons license for non-commercial use.
-  - Commercial use is subject to a commercial agreement with BRIA. To purchase a commercial license simply click [Here](https://go.bria.ai/3B4Asxv).
+  - Commercial use is subject to a commercial agreement with BRIA. [Contact Us](https://bria.ai/contact-us) for more information. 
 
 - **Model Description:** BRIA RMBG 1.4 is a saliency segmentation model trained exclusively on a professional-grade dataset.
 - **BRIA:** Resources for more information: [BRIA AI](https://bria.ai/)
@@ -161,9 +150,9 @@ result=model(image)
 result_image = postprocess_image(result[0][0], orig_im_size)
 
 # save result
-pil_mask_im = Image.fromarray(result_image)
+pil_im = Image.fromarray(result_image)
+no_bg_image = Image.new("RGBA", pil_im.size, (0,0,0,0))
 orig_image = Image.open(image_path)
-no_bg_image = orig_image.copy()
-no_bg_image.putalpha(pil_mask_im)
+no_bg_image.paste(orig_image, mask=pil_im)
 ```
 

example_inference.py

@@ -28,10 +28,10 @@ def example_inference():
     result_image = postprocess_image(result[0][0], orig_im_size)
 
     # save result
-    pil_mask_im = Image.fromarray(result_image)
+    pil_im = Image.fromarray(result_image)
+    no_bg_image = Image.new("RGBA", pil_im.size, (0,0,0,0))
     orig_image = Image.open(im_path)
-    no_bg_image = orig_image.copy()
-    no_bg_image.putalpha(pil_mask_im)    
+    no_bg_image.paste(orig_image, mask=pil_im)
     no_bg_image.save("example_image_no_bg.png")