Image Segmentation
BiRefNet
Safetensors
background-removal
mask-generation
Dichotomous Image Segmentation
Camouflaged Object Detection
Salient Object Detection
pytorch_model_hub_mixin
model_hub_mixin
custom_code
Instructions to use ZhengPeng7/BiRefNet_lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use ZhengPeng7/BiRefNet_lite with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("ZhengPeng7/BiRefNet_lite", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("ZhengPeng7/BiRefNet_lite") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Complete the MIT license in the model card.
Verified signatureaa62cd8
-
Fix the no attribute 'all_tied_weights_keys' issue in transformers==5.0.0.
7838f1c -
For the compatibility with the meta device used in transformers==5.0.0.
fc1aedc
-
Upgrade the ways of importing timm modules (>=1.0.23).
8341833
-
For the compatibility with the latest transformers lib.
Verified signatureaa5bf0a
-
Fix the bug by latest transformers and update req.txt.
1badd0f
-
Add half precision setting in README.
7d10348
-
Align lib_name as birefnet and add inference endpoint option.
b9a7bec
-
Dtype adaptability between FP32 and FP16 in inference.
Verified signature47eae03
-
Update the bibtex.
Verified signature8ca692e
-
Update birefnet.py
Verified signature75a7017
-
Update README.md
Verified signature841caaf
-
Update config.json
Verified signature40a75d6 -
Rename BiRefNet_T to BiRefNet_lite.
Verified signature80b33a4
-
Correct the `_name_or_path ` in config.json.
Verified signatureb6ce8c8 -
Correct `_name_or_path` in config.json.
Verified signature849df25
-
Initial uploading of the BiRefNet for general use with swin_v1_tiny as the backbone.
224e902 -
initial commit
Verified signature2aa9cb5