Upload README.md with huggingface_hub

Upload lama_512_int8.onnx with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload lama_512_fp16.onnx with huggingface_hub

update model card: recommend fp16 over int8

update model card: add int8 model, example images, full benchmark

add example image: examples/example_inpainted_int8.jpg

add example image: examples/example_inpainted_fp16.jpg

add example image: examples/example_inpainted_fp32.jpg

add example image: examples/example_mask.png

add example image: examples/example.jpg

add int8 weight-only quantized model (61.5 MB)

update model card: add fp16 model docs

add fp16 weight-only quantized model (110 MB)

Add lama.onnx

Add README

Upload lama_fp32.onnx

initial commit