angcyo

1 27

https://github.com/angcyo

AI & ML interests

2023-5-31

Recent Activity

liked a model 5 days ago

briaai/RMBG-1.4

liked a model 5 days ago

mujibanget/rmbg-onnx

liked a model 5 days ago

shadow-cann/hispark-modelzoo-yolov8s-obb

View all activity

Organizations

liked 5 models 5 days ago

liked a model 6 days ago

onnx-community/BiRefNet_512x512-ONNX

Image Segmentation • Updated Mar 7, 2025 • 807 • 3

liked 4 models 7 days ago

onnx-community/BiRefNet_lite-ONNX

Image Segmentation • Updated Oct 26, 2025 • 6.78k • 21

studioludens/birefnet-lite-512

Image Segmentation • Updated Apr 17 • 2.45k • 4

ZhengPeng7/BiRefNet_lite-2K

Image Segmentation • 44.4M • Updated Feb 4 • 1.21k • 9

ZhengPeng7/BiRefNet_lite

Image Segmentation • 44.4M • Updated Feb 4 • 17.2k • 19

upvoted a collection 7 days ago

BiRefNet

Collection

A collection of my BiRefNet models -- different tasks, different scales. • 18 items • Updated Nov 9, 2025 • 10

reacted to ZhengPeng7's post with 👍 7 days ago

Post

8764

We just released the [BiRefNet_HR]( ZhengPeng7/BiRefNet_HR) for general use on higher resolution images, which was trained with images in 2048x2048. If your images are mostly larger than 1024x1024, use BiRefNet_HR for better results! Thanks to @Freepik for the kind support of H200s for this huge training.

HF Model: ZhengPeng7/BiRefNet_HR.
HF Demo: ZhengPeng7/BiRefNet_demo, where you need to choose General-HR and set high resolution.
PyTorch weights & ONNX: in Google Drive and the GitHub release.

Here is a comparison between the results of the original one and the new HR one on HR inputs:

And, the performance of this new HR one and the previous one trained in 1024x1024 on val set: