ai4bharat/IndicF5
Text-to-Speech • 0.4B • Updated • 34.7k • 399
Aaquib Badarpura
wolf-AB
·
AI & ML interests
None yet
Recent Activity
liked a model 2 months ago
ai4bharat/IndicF5 reacted to ZhengPeng7's post with 👀 over 1 year 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:
Organizations
None yet
liked a
model 2 months ago
reacted to ZhengPeng7's post with 👀 over 1 year ago
Post
9,289
We just released the [BiRefNet_HR]( ZhengPeng7/BiRefNet_HR) for general use on higher resolution images, which was trained with images in
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
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: