Instructions to use Wan-AI/Wan2.1-T2V-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.1-T2V-14B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-14B", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Apple Silicon compatibility
#8
by ffgg8686 - opened
I guess the answer is likely no, but I just wanted to know if this model is compatible with Apple Silicon at this time, and if not, do you have any plan to make it compatible in the future? Thanks.
I does work on Apple M. chips with the right workflow.
This works:
https://blog.comfy.org/p/wan21-video-model-native-support
In the UI switch sampler to Euler with scheduler normal.
Probably can be optimized much more.