Thijs
ThijsL202
AI & ML interests
None yet
Recent Activity
reacted
to
ZhengPeng7's
post
with 👍
about 18 hours ago
We just released the [BiRefNet_HR](https://huggingface.co/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: https://huggingface.co/ZhengPeng7/BiRefNet_HR.
HF Demo: https://huggingface.co/spaces/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:
liked
a model
1 day ago
hexgrad/Kokoro-82M
liked
a model
3 days ago
6DammK9/AstolfoMix-XL
Organizations
None yet
Collections
4
models
8
ThijsL202/Pantheon-RP-Pure-X-Cydonia-UB-v1.3-36B-Q6_K-GGUF
Updated
•
14
ThijsL202/Pantheon-RP-Pure-X-Cydonia-UB-v1.3-36B
Text Generation
•
Updated
•
12
ThijsL202/Pantheon-RP-Pure-X-Cydonia-UB-v1.3-36B-Q5_K_M-GGUF
Updated
•
11
ThijsL202/Eva-Qwentile2.5-32B
Text Generation
•
Updated
•
14
ThijsL202/Eva-Qwentile2.5-32B-Q6_K-GGUF
Updated
•
21
ThijsL202/magnum-v4-27b-GGUF-0
Updated
•
1
ThijsL202/MadMix-Unleashed-12B-GGUF-0
Updated
•
3
•
1
ThijsL202/MadMix-Unleashed-12B
Text Generation
•
Updated
•
45
•
4
datasets
None public yet