---
title: Wan2.2-I2V-Fly
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.2-I2V-Fly"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.2-I2V-Fly.md"
repository: AI-ModelScope/Wan2.2-I2V-Fly
last_updated: 2025-09-26
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
base_model:
  - Wan-AI/Wan2.2-I2V-A14B
base_model_relation: adapter
parameters: 153.4M
tensor_type:
  - BF16
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 97
stars: 0
tags:
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# Wan2.2-I2V-Fly

> Wan2.2-I2V-Fly - AI-ModelScope 在 ModelScope 开源的模型。starsfriday LoRA for Wan2.2-I2V-A14B Overview This LoRA is trained on the Wan2.2-I2V-A14B model.

AI-ModelScope/Wan2.2-I2V-Fly 是 ModelScope 魔搭社区上的 153.4M 参数image-to-video模型，采用 apache-2.0 许可，基于 Wan-AI/Wan2.2-I2V-A14B 构建。

- **Repository**: AI-ModelScope/Wan2.2-I2V-Fly
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 153.4M
- **Base model**: Wan-AI/Wan2.2-I2V-A14B
- **Tags**: lora, diffusers, template:diffusion-lora
- **Downloads**: 97
- **Stars**: 0
- **Last updated**: 2025-09-26

Source: https://www.modelscope.cn/models/AI-ModelScope/Wan2.2-I2V-Fly

---

<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
  <h1 style="color: #24292e; margin-top: 0;">starsfriday LoRA for Wan2.2-I2V-A14B</h1>
  
  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
    <h2 style="color: #24292e; margin-top: 0;">Overview</h2>
    <p>This LoRA is trained on the Wan2.2-I2V-A14B model.</p>
  </div>

  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
    <h2 style="color: #24292e; margin-top: 0;">Features</h2>
    <ul style="margin-bottom: 0;">
      <li>Generate any life videos of eva through prompt</li>
      <li>Trained on the Wan2.2-I2V-A14B base model</li>
      <li>Consistent results across different object types</li>
      <li>Simple prompt structure that's easy to adapt</li>
    </ul>
  </div>

<Gallery />

# Model File and Inference Workflow

## 📥 Download Links:

- [wan2.2_fly_i2v_high](./wan2.2_fly_i2v_high.safetensors) - LoRA Model File


---
<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
    <h2 style="color: #24292e; margin-top: 0;">Recommended Settings</h2>
    <ul style="margin-bottom: 0;">
      <li><b>LoRA Strength:</b> 1.0</li>
      <li><b>Embedded Guidance Scale:</b> 1.0</li>
      <li><b>Flow Shift:</b> 8.0</li>
    </ul>
  </div>

  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
    <h2 style="color: #24292e; margin-top: 0;">Trigger Words</h2>
    <p>The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">feixing</code></p>
  </div>

  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
    <h2 style="color: #24292e; margin-top: 0;">Prompt Template</h2>
    <p>For best results, use this prompt structure:</p>
    <div style="background-color: #f0f0f0; padding: 12px; border-radius: 6px; margin: 10px 0;">
      <i>这个男人以超人的姿态水平悬空，身体紧贴着地面高速飞行，feixing</i>
    </div>
  </div>