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 comparisons/optimization-v2/decoder-portrait/trials.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 2.5 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/decoder-portrait/trials.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-portrait/trials.json
-
curl -L -o trials.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/decoder-portrait/trials.json
2.5 kB
| { | |
| "source_trace": "outputs/optimization-v2/portrait/wired-baseline-2.trace.safetensors", | |
| "scope": "Same final latent, decoder-only hot latency", | |
| "trials": [ | |
| { | |
| "variant": "native-b1", | |
| "median_ms": 5739.497271017171, | |
| "min_ms": 4017.139167059213, | |
| "max_ms": 7461.85537497513, | |
| "samples_ms": [ | |
| 4017.139167059213, | |
| 7461.85537497513 | |
| ], | |
| "pixel_identical": true, | |
| "mae_8bit": 0.0, | |
| "max_error_8bit": 0, | |
| "psnr_db": null, | |
| "ssim_rgb": 1.0 | |
| }, | |
| { | |
| "variant": "native-b4", | |
| "median_ms": 2673.0494999792427, | |
| "min_ms": 2542.4729590304196, | |
| "max_ms": 2803.626040928066, | |
| "samples_ms": [ | |
| 2803.626040928066, | |
| 2542.4729590304196 | |
| ], | |
| "pixel_identical": true, | |
| "mae_8bit": 0.0, | |
| "max_error_8bit": 0, | |
| "psnr_db": null, | |
| "ssim_rgb": 1.0 | |
| }, | |
| { | |
| "variant": "compiled-b4", | |
| "median_ms": 1929.837999981828, | |
| "min_ms": 1923.4352498315275, | |
| "max_ms": 1936.2407501321286, | |
| "samples_ms": [ | |
| 1923.4352498315275, | |
| 1936.2407501321286 | |
| ], | |
| "pixel_identical": true, | |
| "mae_8bit": 0.0, | |
| "max_error_8bit": 0, | |
| "psnr_db": null, | |
| "ssim_rgb": 1.0 | |
| }, | |
| { | |
| "variant": "native-b8", | |
| "median_ms": 2293.3986249845475, | |
| "min_ms": 2273.374166805297, | |
| "max_ms": 2313.423083163798, | |
| "samples_ms": [ | |
| 2313.423083163798, | |
| 2273.374166805297 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.15126427014668783, | |
| "max_error_8bit": 5, | |
| "psnr_db": 55.96620402076142, | |
| "ssim_rgb": 0.9991664658666948 | |
| }, | |
| { | |
| "variant": "compiled-b8", | |
| "median_ms": 1663.6835205135867, | |
| "min_ms": 1553.2039999961853, | |
| "max_ms": 1774.163041030988, | |
| "samples_ms": [ | |
| 1553.2039999961853, | |
| 1774.163041030988 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.15126427014668783, | |
| "max_error_8bit": 5, | |
| "psnr_db": 55.96620402076142, | |
| "ssim_rgb": 0.9991664658666948 | |
| }, | |
| { | |
| "variant": "coreml-CPU_AND_GPU", | |
| "median_ms": 1591.182250645943, | |
| "min_ms": 1500.6745841819793, | |
| "max_ms": 1681.6899171099067, | |
| "samples_ms": [ | |
| 1500.6745841819793, | |
| 1681.6899171099067 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.2621665795644124, | |
| "max_error_8bit": 11, | |
| "psnr_db": 53.128439249639484, | |
| "ssim_rgb": 0.998681981765892 | |
| } | |
| ] | |
| } | |