Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

lightx2v
/
Wan2.2-I2V-A14B-Moe-Distill-Lightx2v

Image-to-Video
Diffusers
Safetensors
Diffusion Single File
English
Chinese
video generation
comfyui
distillation
LoRA
Model card Files Files and versions
xet
Community
8

Instructions to use lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v 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("lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v", dtype=torch.bfloat16, device_map="cuda")
    pipe.to("cuda")
    
    prompt = "A man with short gray hair plays a red electric guitar."
    image = load_image(
        "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png"
    )
    
    output = pipe(image=image, prompt=prompt).frames[0]
    export_to_video(output, "output.mp4")
  • Diffusion Single File

    How to use lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v 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
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

change 'LoRA' tag to lowercase 'lora'

#8 opened 8 months ago by
linoyts

What is the differents between this MoE-Distill repo, Wan2.2-lightning and Wan2.2-Distill-Loras?

2
#7 opened 8 months ago by
underspirit

lora still causes slow motion

πŸ˜” 2
6
#6 opened 9 months ago by
ZKong

I got worse result than the previous 3 k-samplers solution

#5 opened 9 months ago by
lvsemi

lora error and bad results

2
#4 opened 9 months ago by
ZKong

Wan2.2 Comfyui Working Guide (Open Discussion)

16
#3 opened 9 months ago by
darkstorm2150

Why are there k_img and v_img in the low noise lora?

4
#2 opened 9 months ago by
woctordho

some introduction? how to use ? What is the difference from the historical version? :)

πŸ˜”πŸš€ 3
4
#1 opened 9 months ago by
huiyu9144
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs