Instructions to use SceneWorks/bernini-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/bernini-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir bernini-mlx SceneWorks/bernini-mlx
- Wan2.2
How to use SceneWorks/bernini-mlx with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "boundary_ratio": 0.417, | |
| "clip_diff_cfg": { | |
| "diffusion_batch_mul": 16, | |
| "model_type": "flow_match", | |
| "shift": 2.0, | |
| "target_channels": 3584, | |
| "width": 4096, | |
| "z_channels": 3584 | |
| }, | |
| "connector_cfg": { | |
| "enable_gen_branch": true, | |
| "enable_vit_branch": true, | |
| "gen_head_type": "zerolinear", | |
| "model_type": "MLPConnector", | |
| "out_dim_for_gen": 4096, | |
| "out_dim_for_vit": 3584, | |
| "zero_init_proj_gen_last": true | |
| }, | |
| "feature_type_from_stage_one": "masked_tgt_embed_with_qwen_txt_vit_tokens", | |
| "interpolate_src_id": true, | |
| "max_sequence_length": 512, | |
| "max_trained_src_id": 5, | |
| "num_mask_token": 4096, | |
| "shift": 3.0, | |
| "switch_dit_boundary": 0.875, | |
| "t5_combine_type": "concat_with_zero_init", | |
| "t5_max_sequence_length": 512, | |
| "target_fps": 16, | |
| "use_src_id_rotary_emb": true | |
| } |