Image Segmentation
BEN2
ONNX
Safetensors
PyTorch
BEN2
background-remove
mask-generation
Dichotomous image segmentation
background remove
foreground
background
remove background
model_hub_mixin
pytorch_model_hub_mixin
background removal
background-removal
Instructions to use PramaLLC/BEN2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BEN2
How to use PramaLLC/BEN2 with BEN2:
import requests from PIL import Image from ben2 import AutoModel url = "https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg" image = Image.open(requests.get(url, stream=True).raw) model = AutoModel.from_pretrained("PramaLLC/BEN2") model.to("cuda").eval() foreground = model.inference(image) - Notebooks
- Google Colab
- Kaggle
After removing the background, the images lose some of their color.
#4
by elenopes - opened
This is just an example
I noticed that I can even resave the images or process them in another editor. This does not change the fact that they lose some of the color.
And this is not a bad removal of the background itself, I have examples where the background is removed normally, but the image itself is slightly discolored.
Hello, this is a problem with the model itself. We are working on an improved BEN2.5, and this issue should be fixed after that release in about a week or two.
You are the best!
MaxwellMeyer changed discussion status to closed

