Text-to-Image
MLX
mflux
English
apple-silicon
diffusion
mmdit
flow-matching
krea
quantized
8-bit precision
Instructions to use avlp12/Krea-2-Turbo-Alis-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use avlp12/Krea-2-Turbo-Alis-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download avlp12/Krea-2-Turbo-Alis-MLX-8bit --local-dir Krea-2-Turbo-Alis-MLX-8bit
- mflux
How to use avlp12/Krea-2-Turbo-Alis-MLX-8bit with mflux:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add config.json so the Hub can count downloads (library_name mlx has no countDownloads rule → falls back to config.json)
Browse files- config.json +9 -0
config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "mlx",
|
| 3 |
+
"pipeline_tag": "text-to-image",
|
| 4 |
+
"base_model": "krea/Krea-2-Turbo",
|
| 5 |
+
"architecture": "single-stream MMDiT · 28 blocks · width 6144 · flow-matching · 8-step Turbo",
|
| 6 |
+
"quantization": { "framework": "mlx", "bits": 8, "note": "see krea2/quant_recipes.py" },
|
| 7 |
+
"weights": "transformer_8bit.safetensors",
|
| 8 |
+
"note": "Pure-MLX port, loaded by the bundled krea2/ code (generate.py / app.py), not transformers/diffusers. config.json is included so the Hub can count downloads."
|
| 9 |
+
}
|