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("Leon1000/Wan2.2-I2V-KungFu")
prompt = "一个小孩双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong"
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")valiantcat LoRA for Wan2.2-I2V-A14B
Overview
This LoRA is trained on the Wan2.2-I2V-A14B model.
Features
- Generate any life videos of eva through prompt
- Trained on the Wan2.2-I2V-A14B base model
- Consistent results across different object types
- Simple prompt structure that's easy to adapt
- Prompt
- 一个小孩双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Prompt
- 一个小动物双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Prompt
- 一个小动物双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Prompt
- 一个男人双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Prompt
- 一个女人双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Prompt
- 一个小孩双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
Model File and Inference Workflow
📥 Download Links:
- wan2.2_wugong_i2v_high - LoRA Model File
- wan2.2_wugong_i2v_low - LoRA Model File
Recommended Settings
- LoRA Strength: 1.0
- Embedded Guidance Scale: 1.0
- Flow Shift: 8.0
Trigger Words
The key trigger phrase is: wugong
Prompt Template
For best results, use this prompt structure:
一个小孩双脚直立，双臂灵活张开，时而抬手，然后转身朝向左边，时而踢腿，做着一系列打拳动作，wugong
- Downloads last month
- 52
Model tree for Leon1000/Wan2.2-I2V-KungFu
Base model
Wan-AI/Wan2.2-I2V-A14B