Instructions to use lightx2v/LightWan2.2-A14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/LightWan2.2-A14B 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/LightWan2.2-A14B", torch_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
ConvRot models
#7
by monstari - opened
Hi LightX2V team,
First of all, thank you for your incredible work on optimizing Wan2.2 14B!
The ConvRot INT8 format, which provides a significant speedup on these generations over FP8/GGUF while maintaining high video fidelity, would it be possible for you to release an INT8 ConvRot version of this LightWan2.2-A14B model?
Thank you for considering this request!