Instructions to use Wan-AI/Wan2.1-T2V-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.1-T2V-1.3B 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-1.3B", 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
Multi GPU Support?
#13
by ZiggyS - opened
This may be a comfyui node limitation as im using that interface in this case to try this out, and if so ill ask over there instead, but i thought id start here in case its a model limitation of some sort.
I have 2 GPUs, but only one gets used, and so i run out of ram any time i extend the number of frames a bit too much.
me too - did you find a solution ?
me too - did you find a solution ?
Nope.