---
title: Wan2.1-Mecha-LoRA
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.1-Mecha-LoRA"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.1-Mecha-LoRA.md"
repository: AI-ModelScope/Wan2.1-Mecha-LoRA
last_updated: 2026-06-16
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
base_model:
  - Wan-AI/Wan2.1-I2V-14B-720P
  - Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
base_model_relation: adapter
parameters: 179.6M
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 119
stars: 0
tags:
  - text-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# Wan2.1-Mecha-LoRA

> Wan2.1-Mecha-LoRA - AI-ModelScope 在 ModelScope 开源的模型。starsfriday LoRA for Wan2.1 14B I2V 720p Overview This LoRA is trained on the Wan2.1 14B I2V 720p model.

AI-ModelScope/Wan2.1-Mecha-LoRA 是 ModelScope 魔搭社区上的 179.6M 参数image-to-video模型，采用 apache-2.0 许可，基于 Wan-AI/Wan2.1-I2V-14B-720P、Wan-AI/Wan2.1-I2V-14B-720P-Diffusers 构建。

- **Repository**: AI-ModelScope/Wan2.1-Mecha-LoRA
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 179.6M
- **Base model**: Wan-AI/Wan2.1-I2V-14B-720P, Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
- **Tags**: text-to-image, lora, diffusers, template:diffusion-lora
- **Downloads**: 119
- **Stars**: 0
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/AI-ModelScope/Wan2.1-Mecha-LoRA

---

<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
  <h1 style="color: #24292e; margin-top: 0;">starsfriday LoRA for Wan2.1 14B I2V 720p</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 Wan2.1 14B I2V 720p 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>Transform any image into a video of two people began to fight</li>
      <li>Trained on the Wan2.1 14B 720p I2V 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:

- [wan2.1-Mecha.safetensors](./wan2.1-Mecha.safetensors) - LoRA Model File
- [wan_img2video_lora_workflow.json](./result/wan2.1-exmple.json) - Wan I2V with LoRA Workflow for ComfyUI

## Using with Diffusers
```py
pip install git+https://github.com/huggingface/diffusers.git
```

```py
import torch
from diffusers.utils import export_to_video, load_image
from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
from transformers import CLIPVisionModel
import numpy as np

model_id = "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16)
pipe.to("cuda")

pipe.load_lora_weights("starsfriday/Wan2.1-Mecha-LoRA")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "gangtiexia，背景保持不变，这个人开始变身红色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走."

image = load_image("https://huggingface.co/starsfriday/Wan2.1-Mecha-LoRA/blob/main/result/test.jpg")

max_area = 512 * 768
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
image = image.resize((width, height))

output = pipe(
    image=image,
    prompt=prompt,
    height=height,
    width=width,
    num_frames=81,
    guidance_scale=5.0,
    num_inference_steps=25
).frames[0]
export_to_video(output, "output.mp4", fps=16)
```

---
<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> 6.0</li>
      <li><b>Flow Shift:</b> 5.0</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;">gangtiexia</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>gangtiexia，背景保持不变，这个人开始变身[color]色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走</i>
    </div>
    <p>Simply replace <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">[color]</code> with whatever you want to let this person transform into the color of a mecha</p>
  </div>