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-product/comparison/metrics.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 3.27 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/decoder-product/comparison/metrics.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/comparison/metrics.json
-
curl -L -o metrics.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/decoder-product/comparison/metrics.json
3.27 kB
| { | |
| "validation_scope": "Same final latent; decoder only", | |
| "reference": "/Users/devin/Desktop/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/native-b1.png", | |
| "native_size": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "crop_xyxy": [ | |
| 768, | |
| 768, | |
| 1280, | |
| 1280 | |
| ], | |
| "heatmap_gain": 8, | |
| "metric_definition": { | |
| "psnr": "Full-resolution 8-bit RGB MSE, data range 255; null means infinity", | |
| "ssim": "scikit-image RGB structural_similarity, channel_axis=-1, data_range=255, default 7x7 window", | |
| "mae": "Full-resolution mean absolute 8-bit RGB error" | |
| }, | |
| "rows": [ | |
| { | |
| "label": "native-b1", | |
| "image": "/Users/devin/Desktop/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/native-b1.png", | |
| "png_sha256": "63684ef8ae148a35ddef02650c6aa30b4843b47c99b06cec2ea3708ef3fc2293", | |
| "pixel_identical": true, | |
| "mae_8bit": 0.0, | |
| "max_error_8bit": 0, | |
| "psnr_db": null, | |
| "ssim_rgb": 1.0, | |
| "timings": { | |
| "decode_s": 2.870773000176996 | |
| }, | |
| "steps": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "timing_scope": "Warm decoder only; model loading excluded" | |
| }, | |
| { | |
| "label": "native-b8", | |
| "image": "/Users/devin/Desktop/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/native-b8.png", | |
| "png_sha256": "57a85569ad45d469b191470541e8cfff8d576fed6cc6bb8bd54db16e9bd2d81f", | |
| "pixel_identical": false, | |
| "mae_8bit": 0.1251803239186605, | |
| "max_error_8bit": 4, | |
| "psnr_db": 56.9881575908215, | |
| "ssim_rgb": 0.9989046120633382, | |
| "timings": { | |
| "decode_s": 1.9198206248693168 | |
| }, | |
| "steps": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "timing_scope": "Warm decoder only; model loading excluded" | |
| }, | |
| { | |
| "label": "compiled-b8", | |
| "image": "/Users/devin/Desktop/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/compiled-b8.png", | |
| "png_sha256": "57a85569ad45d469b191470541e8cfff8d576fed6cc6bb8bd54db16e9bd2d81f", | |
| "pixel_identical": false, | |
| "mae_8bit": 0.1251803239186605, | |
| "max_error_8bit": 4, | |
| "psnr_db": 56.9881575908215, | |
| "ssim_rgb": 0.9989046120633382, | |
| "timings": { | |
| "decode_s": 1.5638958329800516 | |
| }, | |
| "steps": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "timing_scope": "Warm decoder only; model loading excluded" | |
| }, | |
| { | |
| "label": "coreml-CPU_AND_GPU", | |
| "image": "/Users/devin/Desktop/MiniMax-H3-Image-mlx/comparisons/optimization-v2/decoder-product/coreml-CPU_AND_GPU.png", | |
| "png_sha256": "36a7cdad88b12839d1e4cd30384ee60fafffaac52d2ba05e3be409a33a40a50a", | |
| "pixel_identical": false, | |
| "mae_8bit": 0.2054581642150879, | |
| "max_error_8bit": 7, | |
| "psnr_db": 54.674052201530415, | |
| "ssim_rgb": 0.9983190643001968, | |
| "timings": { | |
| "decode_s": 1.5556999580003321 | |
| }, | |
| "steps": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "timing_scope": "Warm decoder only; model loading excluded" | |
| } | |
| ], | |
| "interpretation": "Pixel similarity to the same seeded trajectory, not a measure of prompt adherence or perceptual quality." | |
| } | |