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
Download reports/optimization-v2/approximation-quality.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 887 Bytes
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/reports/optimization-v2/approximation-quality.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/reports/optimization-v2/approximation-quality.json
-
curl -L -o approximation-quality.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/reports/optimization-v2/approximation-quality.json
887 Bytes
| [ | |
| { | |
| "case": "product", | |
| "profile": "fp16", | |
| "pixel_identical": false, | |
| "mae_8bit": 154.0353469053904, | |
| "max_error_8bit": 255, | |
| "psnr_db": 3.5187477254843316, | |
| "ssim_rgb": 0.029728687074001295 | |
| }, | |
| { | |
| "case": "product", | |
| "profile": "five-pass", | |
| "pixel_identical": false, | |
| "mae_8bit": 22.355140527089436, | |
| "max_error_8bit": 255, | |
| "psnr_db": 16.798797459226876, | |
| "ssim_rgb": 0.7964514877131589 | |
| }, | |
| { | |
| "case": "portrait", | |
| "profile": "fp16", | |
| "pixel_identical": false, | |
| "mae_8bit": 104.15469749768575, | |
| "max_error_8bit": 255, | |
| "psnr_db": 5.980561568481523, | |
| "ssim_rgb": 0.02374704438244847 | |
| }, | |
| { | |
| "case": "portrait", | |
| "profile": "five-pass", | |
| "pixel_identical": false, | |
| "mae_8bit": 25.05439265569051, | |
| "max_error_8bit": 253, | |
| "psnr_db": 17.022613207270645, | |
| "ssim_rgb": 0.6941111421384556 | |
| } | |
| ] | |