Wan2.1-Mecha-LoRA

<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;"> <h1 style="color: #24292e; margin-top: 0;">valiantcat 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 - LoRA Model File
• wan_img2video_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

Using with Diffusers

pip install git+https://github.com/huggingface/diffusers.git

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("valiantcat/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/valiantcat/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>