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
Inquiry: Diffusers Support for Wan2.2‑Lightning Model
#33
by alfredplpl - opened
Hello,
I have a question regarding the lightx2v/Wan2.2-Lightning model (the distilled version of the Wan2.2 family).
It appears that this model is currently provided mainly for text-to-video / image-to-video usage and ComfyUI, but I couldn’t find any support for usage via the Diffusers pipelines.
Meanwhile, other Wan2.2 models—such as Wan2.2-T2V-A14B, Wan2.2-I2V-A14B, and Wan2.2-TI2V-5B—seem to have already been integrated into the Diffusers library.
Therefore, I’d like to ask:
- Is there any plan to add Diffusers support for the Wan2.2-Lightning model?
- If not currently supported, are there plans or instructions on how to contribute support?
- Also, is there any guidance on how the community can contribute a community pipeline to Diffusers, or invitation to help with the integration?
Thank you very much for your guidance and support.
OK. I could load the models. Thanks.
alfredplpl changed discussion status to closed