Instructions to use Wan-AI/Wan2.2-S2V-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.2-S2V-14B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-S2V-14B", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Official Lightning Lora from Wan-AI?
#12
by Wladastic - opened
Is there going to come a lightning Lora made by Wan-AI themselves?
S2V did not receive one as far as I know and I would really like to create one but lack the computational capabilities.
Such Lora might significantly improve the usage of S2V and improve the models' popularity even further.
Currently I am using lightx2v T2V cfg step distill v2 rank64 bf16 at strength of 1.
I tried different ones, maybe I could also try using the ones for low noise wan 2.2 as well.
But funnily the mentioned lora works with cfg 6 very well.