Text-to-Image
MLX
MiniMax H3
Safetensors
English
apple-silicon
macos
image-to-image
image-editing
image-generation
Instructions to use devin-lai/MiniMax-H3-Image-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use devin-lai/MiniMax-H3-Image-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download devin-lai/MiniMax-H3-Image-mlx --local-dir MiniMax-H3-Image-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
File size: 604 Bytes
3da88e3 | 1 2 3 4 5 6 7 8 9 10 | {
"files": {
"h3_mlx/compare.py": "78a48ea24967c7a6349ed1e50cc1dab690f4c90e65939624d82bb0b146126095",
"h3_mlx/reference.py": "7a08f60e3d21c708f71112a2f012356faff45042e43cc0a0627693421d9d4e3e",
"tests/test_numerics.py": "373eb2f050ae101316dfd3a5f8a86eb74ceda98e180690b5c22094b4aad106dc"
},
"exact_metric": "maximum absolute decoded uint8 pixel error over all cases; nonfinite trace values must be zero",
"numerical_screen": "Only if separately classified: per-case SSIM >=0.9995, MAE <=0.1/255, max RGB error <=4; visual crop review still required. No promotion from metrics alone."
}
|