Instructions to use mlx-community/MOSS-Image-Base-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MOSS-Image-Base-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/MOSS-Image-Base-bf16 --local-dir MOSS-Image-Base-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download vae/config.json from mlx-community/MOSS-Image-Base-bf16: direct link, hf CLI and curl.
- Browser
- Download file 838 Bytes
-
https://huggingface.co/mlx-community/MOSS-Image-Base-bf16/resolve/main/vae/config.json
- Command line
-
hf download hf://mlx-community/MOSS-Image-Base-bf16/vae/config.json
-
curl -L -o config.json https://huggingface.co/mlx-community/MOSS-Image-Base-bf16/resolve/main/vae/config.json
838 Bytes
| { | |
| "_class_name": "AutoencoderKLFlux2", | |
| "_diffusers_version": "0.38.0", | |
| "act_fn": "silu", | |
| "batch_norm_eps": 0.0001, | |
| "batch_norm_momentum": 0.1, | |
| "block_out_channels": [ | |
| 128, | |
| 256, | |
| 512, | |
| 512 | |
| ], | |
| "decoder_block_out_channels": [ | |
| 96, | |
| 192, | |
| 384, | |
| 384 | |
| ], | |
| "down_block_types": [ | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D", | |
| "DownEncoderBlock2D" | |
| ], | |
| "force_upcast": true, | |
| "in_channels": 3, | |
| "latent_channels": 32, | |
| "layers_per_block": 2, | |
| "mid_block_add_attention": true, | |
| "norm_num_groups": 32, | |
| "out_channels": 3, | |
| "patch_size": [ | |
| 2, | |
| 2 | |
| ], | |
| "sample_size": 1024, | |
| "up_block_types": [ | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D", | |
| "UpDecoderBlock2D" | |
| ], | |
| "use_post_quant_conv": true, | |
| "use_quant_conv": true | |
| } | |