Instructions to use lightx2v/Wan2.2-Distill-Loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan2.2-Distill-Loras with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-I2V-A14B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lightx2v/Wan2.2-Distill-Loras") prompt = "A man with short gray hair plays a red electric guitar." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Diffusion Single File
How to use lightx2v/Wan2.2-Distill-Loras with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
Update 2025-10-17 Lora, ghosting/blur
The lora produces always ghosting/blur on this tested settings:
4 steps, cfg 1 - multiple images tested, 592x848,
euler+simple
euler+normal
euler+beta
lcm+ltx
Anyone got this working?
The lora produces always ghosting/blur on this tested settings:
4 steps, cfg 1 - multiple images tested, 592x848,
euler+simple
euler+normal
euler+beta
lcm+ltxAnyone got this working?
Yes Me, all you need just make 8 steps and split them into 4 for high steps and 4 for low steps, and the results will be great. And i also tried with 10 steps and still got good results.
The LoRA has been updated. Its filename is suffixed with the timestamp "1022" β we recommend trying it with the 4-step + Euler scheduler.