Instructions to use SceneWorks/z-image-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/z-image-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir z-image-mlx SceneWorks/z-image-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_class_name": "AutoencoderKL", | |
| "_diffusers_version": "0.30.0.dev0", | |
| "_name_or_path": "../checkpoints/flux-dev", | |
| "act_fn": "silu", | |
| "block_out_channels": [ | |
| 128, | |
| 256, | |
| 512, | |
| 512 | |
| ], | |
| "down_block_types": [ | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D" | |
| ], | |
| "force_upcast": true, | |
| "in_channels": 3, | |
| "latent_channels": 16, | |
| "latents_mean": null, | |
| "latents_std": null, | |
| "layers_per_block": 2, | |
| "mid_block_add_attention": true, | |
| "norm_num_groups": 32, | |
| "out_channels": 3, | |
| "sample_size": 1024, | |
| "scaling_factor": 0.3611, | |
| "shift_factor": 0.1159, | |
| "up_block_types": [ | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D" | |
| ], | |
| "use_post_quant_conv": false, | |
| "use_quant_conv": false, | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 64 | |
| } | |
| } |