Upload a picture, our model will extract a highly accurate segmentation of the subject in it.
) The resolution used in our training was 1024x1024, thus the suggested resolution to obtain good results!
Our codes can be found at https://github.com/ZhengPeng7/BiRefNet.
We also maintain the HF model of BiRefNet at https://huggingface.co/ZhengPeng7/BiRefNet for easier access.