Muscle Open Source Model - Free to Convert Image Characters into Stunning Videos Showing Muscles!

Muscle

Developed by Remade-AI

A LoRA trained on the Wan2.1 14B I2V 480p model, capable of transforming characters in images into muscle-displaying videos.

EnglishOpen Source License:Apache-2.0 #Image to Muscle Video #LoRA Fine-tuning #Character Muscle Display

Downloads 1,877

Release Time : 3/11/2025

Model Overview

This LoRA model can convert input images into videos showcasing character muscles, suitable for various muscle display scenarios of different character types.

Model Features

Muscle Display Effect

Can transform any character in an image into a video showcasing well-developed muscles.

Based on Wan2.1 Model

Trained on the Wan2.1 14B 480p I2V base model.

Consistent Performance

Performs consistently across different object types.

Simple Prompt Structure

Uses an easy-to-adjust prompt structure to generate effects.

Model Capabilities

Image to Video

Character Transformation

Muscle Effect Generation

Use Cases

Entertainment Applications

Celebrity Muscle Display

Convert celebrity images into videos showcasing muscles.

example_videos/trump_muscle.mp4

Ordinary Character Muscle Display

Convert ordinary people's images into videos showcasing muscles.

example_videos/man1_muscle.mp4

🚀 Muscle Show-Off Effect LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling you to add muscles to anyone in an image!

🚀 Quick Start

Model File and Inference Workflow

📥 Download Links:

muscle_18_epochs.safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

✨ Features

Transform any image into a video of the subject showing off developed muscles.
Trained on the Wan2.1 14B 480p I2V base model.
Consistent results across different object types.
Simple prompt structure that's easy to adapt.

👥 Community

Discord: Join our community to generate videos with this LoRA for free.
Request LoRAs: We're training and open - sourcing Wan2.1 LoRAs for free. Join our Discord to make requests!

🛠️ Recommended Settings

Property	Details
LoRA Strength	1.0
Embedded Guidance Scale	6.0
Flow Shift	5.0

🔑 Trigger Words

The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">t2k1s takes off clothes revealing a lean muscular body and shows off muscles</code>

💡 Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

🖥️ ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

Workflow Screenshot

See the Downloads section above for the modified workflow.

📚 Model Information

The model weights are available in Safetensors format. See the Downloads section above.

📈 Training Details

Property	Details
Base Model	Wan2.1 14B I2V 480p
Training Data	Trained on 30 seconds of video comprised of 12 short clips (each clip captioned separately) of people showing off their muscles
Epochs	18

➕ Additional Information

Training was done using Diffusion Pipe for Training.

🙏 Acknowledgments

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

📄 License

This project is licensed under the Apache - 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご