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
Maybe that helps?
#36
by TheRopeDude - opened
Hey, first of all thanks a lot for your work.
I've been playing with your great Lora for some time and I'm having the same issues as other like less dynamic movements but also (and I didn't see a lot of people talking about that), less expression range, especially in the negatives (feat, anxiety etc...)
I've red that you are working on a new version and that is great but just to help other people and maybe you as well, I've been able to partially "correct" these issues by adding some dynamic related prompts like "quickly, in a fast motion etc..) but most importantly by weighting them like in SD with : "(prompt:2)"
I hope this helps a bit.
Take care and thanks again.
TheRopeDude changed discussion status to closed
TheRopeDude changed discussion status to open