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 optimization/round-03-compact/reference.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 1.35 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/optimization/round-03-compact/reference.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/optimization/round-03-compact/reference.json
-
curl -L -o reference.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/optimization/round-03-compact/reference.json
1.35 kB
| { | |
| "anchors": { | |
| "product": { | |
| "path": "outputs/optimization-r3/product/control-timed-2.png", | |
| "png_sha256": "63684ef8ae148a35ddef02650c6aa30b4843b47c99b06cec2ea3708ef3fc2293", | |
| "trace_sha256": "40440f8bf2c8f2ab3cbb454ccc9416062b9d69718aa6a0ef9baf1268037b9a29" | |
| }, | |
| "portrait": { | |
| "path": "outputs/optimization-r3/portrait/control-warmup--1.png", | |
| "png_sha256": "32af5e3b95919e79e0019058ec396824c5861f9a43a4fa50c7b20348e8d81933", | |
| "trace_sha256": "5808ccec8c5049ce2761d0b5f41638e28107b287c9e63fe6bef175e600c9c6c8" | |
| }, | |
| "holdout-detail": { | |
| "path": "outputs/optimization-r3/holdout-detail/control-warmup--1.png", | |
| "png_sha256": "ddbfc06c4556c08669d35a4618d380a99998e39a0226e7688d149993ab183038", | |
| "trace_sha256": "ec09215c7aceba45e8174d197b83240ac42daf2538330c33b58591695bfd059d" | |
| }, | |
| "edit": { | |
| "path": "outputs/optimization-r3/edit/control-warmup--1.png", | |
| "png_sha256": "9df3f80efa5ef9f078c9acda81febdbc2d5d706f3c85c574fdfd9fd274b71304", | |
| "trace_sha256": "ab1f86da280c5b355627ea5384dac3ea27b2a3ce23204f5ea66910d83639073c" | |
| } | |
| }, | |
| "foundation_manifest": "provenance/sources.json", | |
| "foundation_sha256": "3274a3e5fe0d2ea0d63f66b020beb193276a0a9d8de7ea466b312fbae9a2746f", | |
| "scope": "Incremental identity to original MLX BF16 recipe, not CUDA/FP32 equality." | |
| } | |