Instructions to use Avdpro/H3-Portrait-Refiner-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Avdpro/H3-Portrait-Refiner-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Avdpro/H3-Portrait-Refiner-MLX --local-dir H3-Portrait-Refiner-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download README.md from Avdpro/H3-Portrait-Refiner-MLX: direct link, hf CLI and curl.
- Browser
- Download file 686 Bytes
-
https://huggingface.co/Avdpro/H3-Portrait-Refiner-MLX/resolve/main/README.md
- Command line
-
hf download hf://Avdpro/H3-Portrait-Refiner-MLX/README.md
-
curl -L -o README.md https://huggingface.co/Avdpro/H3-Portrait-Refiner-MLX/resolve/main/README.md
686 Bytes
metadata
library_name: mlx
license: other
license_name: component-licenses
license_link: https://huggingface.co/Avdpro/H3-Portrait-Refiner-MLX/blob/main/NOTICE.md
pipeline_tag: video-to-video
H3 Portrait Refiner MLX assets
Speech-driven local mouth refinement for AI2Apps H3 Portrait. This bundle contains MuseTalk 1.5 Q4, YuNet 2023mar converted to a portable MLX graph, and BiSeNet BF16. It contains no H3 weights, Runtime, user recordings, or portrait images. Model code is shipped separately by the AI2Apps model Package.
Sources and pinned revisions are recorded in sources.json. Original model cards and component licenses are preserved. See NOTICE.md. No blanket relicensing.