Instructions to use baa-ai/LTX-2.3-22B-RAM-12GB-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use baa-ai/LTX-2.3-22B-RAM-12GB-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download baa-ai/LTX-2.3-22B-RAM-12GB-MLX --local-dir LTX-2.3-22B-RAM-12GB-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download spatial_upscaler_x2_v1_1_config.json from baa-ai/LTX-2.3-22B-RAM-12GB-MLX: direct link, hf CLI and curl.
- Browser
- Download file 275 Bytes
-
https://huggingface.co/baa-ai/LTX-2.3-22B-RAM-12GB-MLX/resolve/debd30eee97a1633f53ef571f78a7d52ff64079f/spatial_upscaler_x2_v1_1_config.json
- Command line
-
hf download hf://baa-ai/LTX-2.3-22B-RAM-12GB-MLX@debd30eee97a1633f53ef571f78a7d52ff64079f/spatial_upscaler_x2_v1_1_config.json
-
curl -L -o spatial_upscaler_x2_v1_1_config.json https://huggingface.co/baa-ai/LTX-2.3-22B-RAM-12GB-MLX/resolve/debd30eee97a1633f53ef571f78a7d52ff64079f/spatial_upscaler_x2_v1_1_config.json
275 Bytes
| { | |
| "config": { | |
| "_class_name": "LatentUpsampler", | |
| "in_channels": 128, | |
| "mid_channels": 1024, | |
| "num_blocks_per_stage": 4, | |
| "dims": 3, | |
| "spatial_upsample": true, | |
| "temporal_upsample": false, | |
| "spatial_scale": 2.0, | |
| "rational_resampler": false | |
| } | |
| } |