Instructions to use dgrauet/matrix-game-3.0-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dgrauet/matrix-game-3.0-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir matrix-game-3.0-mlx dgrauet/matrix-game-3.0-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
dgrauet/matrix-game-3.0-mlx
MLX format conversion of Skywork/Matrix-Game-3.0.
Converted with mlx-forge.
Usage
These weights can be used with Matrix-Game-mlx:
git clone https://github.com/dgrauet/Matrix-Game-mlx.git && cd Matrix-Game-mlx
pip install -r requirements.txt
# weights are downloaded from dgrauet/matrix-game-3.0-mlx on first run
python3 generate.py \
--prompt "A colorful, animated cityscape with a gas station and various buildings." \
--image demo_images/001/image.png
Related Projects
Files
config.json(1.01 KB)dit.safetensors(12.05 GB)dit_distilled.safetensors(24.10 GB)google/umt5-xxl/special_tokens_map.json(6.47 KB)google/umt5-xxl/spiece.model(4.34 MB)google/umt5-xxl/tokenizer.json(16.06 MB)google/umt5-xxl/tokenizer_config.json(60.28 KB)split_model.json(721.00 B)t5_encoder.safetensors(10.58 GB)vae.safetensors(2.63 GB)vae_lightvae.safetensors(675.16 MB)vae_lightvae_v2.safetensors(170.37 MB)
- Downloads last month
- 146
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support