Instructions to use lBroth/FastWan2.2-TI2V-5B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use lBroth/FastWan2.2-TI2V-5B-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir FastWan2.2-TI2V-5B-MLX lBroth/FastWan2.2-TI2V-5B-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
FastWan2.2-TI2V-5B โ MLX (DMD 3-step)
Self-contained MLX conversion of FastVideo/FastWan2.2-TI2V-5B-FullAttn
for Apple-Silicon image-to-video, used as the Fast tier in
Videoboom. DMD-distilled: 3 denoise
steps (sigmas [1.0, 0.757, 0.522, 0.0], guide=1, renoise) via
mlx-video.
Files (self-contained)
| file | size | what |
|---|---|---|
model.safetensors |
10.0 GB | DiT (bf16) |
t5_encoder.safetensors |
11.4 GB | umt5 text encoder |
vae.safetensors |
2.8 GB | VAE |
config.json |
โ | includes the fastwan_dmd marker |
~832ร480 / 121 frames per clip. License Apache-2.0 (inherited from the base model).
- Downloads last month
- 55
Model size
5B params
Tensor type
BF16
ยท
Hardware compatibility
Log In to add your hardware
Quantized