Instructions to use lightx2v/Wan2.2-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan2.2-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lightx2v/Wan2.2-Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
comfyUI workflow release, take a try :)
We have released a workflow, please take a try :)
https://github.com/ModelTC/Wan2.2-Lightning/issues/3
Your feedback is welcome
thnxβ₯β₯β₯
Please lean less heavily on Kijai. Your LoRAs should work with native workflows, but they don't.
Doesnt work in native workflow. Blurry grainy mess, bad quality, horrible results
The latest Workflow T2V-4steps-V1 are now work with WanVideoWrappe
Feel free to use it and enjoy faster video creation ;)
I don't want to use WanVideoWrapper because I have OOM issues running it. You just need to make your LoRAs work with native ComfyUI, which is the standard.
I dont understand what peoples issue is here... the loras work the same as 2.1. Add them to a native flow....
Do you all need someone else to add loras to a workflow. I do not understand how some people will wait for someone else to fix or update a workflow when you need to do 2 things yourself...
Native 2.2 with loras... i used old lightx2v, replace it with lightning.
https://openart.ai/workflows/rocky533/wan-22-14b-image-to-video-fixed/UKQ9BmQs8XVqOHbzDYrm