Text-to-Video
Diffusers
Safetensors
English
text-to-video;
image-to-video;
comfyUI;
video-generation;
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
Which generate.py support --lora_dir ?
#24
by jiangshining - opened
In the instruction of Run Wan2.2-Lightning, it says run cmd python generate.py with --lora_dir, but it seems like there's no param in Wan2.2 official repo. Where are generate.py from?
@jiangshining
Hi, plese use the script with our repo https://github.com/ModelTC/Wan2.2-Lightning/, the --lora_dir argument is in this line https://github.com/ModelTC/Wan2.2-Lightning/blob/main/generate.py#L124
Thank you, it's success in 2min34sec with 4 transformer steps on an A100.
jiangshining changed discussion status to closed