Instructions to use FrankDase/LTX-2.3-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FrankDase/LTX-2.3-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LTX-2.3-MLX FrankDase/LTX-2.3-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "convolution_dimensions": 3, | |
| "encoder_blocks": [ | |
| [ | |
| "res_x", | |
| { | |
| "num_layers": 4 | |
| } | |
| ], | |
| [ | |
| "compress_space_res", | |
| { | |
| "multiplier": 2 | |
| } | |
| ], | |
| [ | |
| "res_x", | |
| { | |
| "num_layers": 6 | |
| } | |
| ], | |
| [ | |
| "compress_time_res", | |
| { | |
| "multiplier": 2 | |
| } | |
| ], | |
| [ | |
| "res_x", | |
| { | |
| "num_layers": 6 | |
| } | |
| ], | |
| [ | |
| "compress_all_res", | |
| { | |
| "multiplier": 2 | |
| } | |
| ], | |
| [ | |
| "res_x", | |
| { | |
| "num_layers": 2 | |
| } | |
| ], | |
| [ | |
| "compress_all_res", | |
| { | |
| "multiplier": 1 | |
| } | |
| ], | |
| [ | |
| "res_x", | |
| { | |
| "num_layers": 2 | |
| } | |
| ] | |
| ], | |
| "encoder_spatial_padding_mode": "zeros", | |
| "in_channels": 3, | |
| "latent_log_var": "uniform", | |
| "norm_layer": "pixel_norm", | |
| "out_channels": 128, | |
| "patch_size": 4 | |
| } |