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
Some NEW* comparisons for you
#64
by PGCRYPT - opened
A comparison of all Lightning LoRA pairs, from oldest to newest.
-All models are set to 1 strenght
-Using FP8_SCALED base models
- T2V 432x768px - EULER / SIMPLE - shift 5 - 41frames
- T2I 1080x1920px - GRADIENT ESTIMATION / BONG TANGENT - shift 5 - 1frame
If you're asking me, I would tell you to use the 250928 pair, much better colors, less "high cfg" oversaturated / bright look, more natural, more overall / fine details.
Maybe try SEKO v2 if you are rendering more synthetic stuff like anime or CGI style.
Thank you for detailed comparison!
Did you test I2V loras?
Super useful thank you! Bookmarking for later. Just need i2v compare as well :) thx thx













