Fix the no attribute 'all_tied_weights_keys' issue in transformers==5.0.0.

For the compatibility with the meta device used in transformers==5.0.0.

Upgrade the ways of importing timm modules (>=1.0.23).

For the compatibility with the latest transformers lib.

Fix the bug by latest transformers and update req.txt.

Align lib_name as birefnet and add inference endpoint option.

Add inference endpoint feature in HF model page.

Add inference endpoint feature.

Add inference endpoint feature.

Add inference endpoint feature.

Add inference endpoint feature.

Add inference endpoint feature.

Add the deployment option.

Update README.md

Add widget in README.

Add the deployment option. Update the model codes.

Add the deployment option.

Add the deployment option.

Add the deployment option.

Dtype adaptability between FP32 and FP16 in inference.

Update the bibtex.

Update birefnet.py

Correct the `_name_or_path ` in config.json.

Update `_name_or_path` in config.json.

Update config.json (#1)

Convert weights to safetensors and add README.

Update README.md

Upload BiRefNet-massive-epoch_240.pth

Update README.md

initial commit