Text-to-Image
MLX
Safetensors
English
Chinese
moss_image
apple-silicon
moss-image
text-rendering
layout
quantized
8-bit precision
Instructions to use VisualInference/MOSS-Image-SFT-MLX-compact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use VisualInference/MOSS-Image-SFT-MLX-compact with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download VisualInference/MOSS-Image-SFT-MLX-compact --local-dir MOSS-Image-SFT-MLX-compact
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download transformer/config.json from VisualInference/MOSS-Image-SFT-MLX-compact: direct link, hf CLI and curl.
- Browser
- Download file 352 Bytes
-
https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-compact/resolve/main/transformer/config.json
- Command line
-
hf download hf://VisualInference/MOSS-Image-SFT-MLX-compact/transformer/config.json
-
curl -L -o config.json https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-compact/resolve/main/transformer/config.json
352 Bytes
| { | |
| "_class_name": "MOSSImageTransformer", | |
| "_diffusers_version": "0.38.0", | |
| "dim": 3072, | |
| "ffn_dim": 8192, | |
| "freq_dim": 256, | |
| "latent_channels": 128, | |
| "num_heads": 24, | |
| "num_layers": 42, | |
| "rope_base": 10000.0, | |
| "text_dim": 4096, | |
| "moss_image_mlx": { | |
| "format": 1, | |
| "quantization": { | |
| "bits": 8, | |
| "group_size": 64 | |
| } | |
| } | |
| } | |