Instructions to use SceneWorks/krea-2-raw-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/krea-2-raw-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir krea-2-raw-mlx SceneWorks/krea-2-raw-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Krea 2 Raw MLX turnkey: bf16 / Q8 / Q4 tiers + README + LICENSE (epic 9992 P3, sc-9995)
8dc5d45 verified | { | |
| "_class_name": "Krea2Transformer2DModel", | |
| "_diffusers_version": "0.39.0.dev0", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 32, | |
| 48, | |
| 48 | |
| ], | |
| "in_channels": 64, | |
| "intermediate_size": 16384, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 48, | |
| "num_key_value_heads": 12, | |
| "num_layers": 28, | |
| "num_layerwise_text_blocks": 2, | |
| "num_refiner_text_blocks": 2, | |
| "num_text_layers": 12, | |
| "rope_theta": 1000.0, | |
| "text_hidden_dim": 2560, | |
| "text_intermediate_size": 6912, | |
| "text_num_attention_heads": 20, | |
| "text_num_key_value_heads": 20, | |
| "timestep_embed_dim": 256 | |
| } | |