Samurai Open-Source Image Conversion LoRA - Free to Transform Image Characters/Objects into Samurai Versions

Samurai

Developed by Remade-AI

A LoRA trained on the Wan2.1 14B I2V 480p model, capable of transforming any person/object in an image into a samurai version.

Text-to-Video EnglishOpen Source License:Apache-2.0 #Samurai transformation effects #Image-to-video #LoRA fine-tuning

Downloads 425

Release Time : 3/15/2025

Model Overview

This LoRA model can convert input images or text descriptions into samurai transformation videos, supporting consistent effects across different object types.

Model Features

Samurai Transformation

Transforms the main subject in any image into a samurai version, supporting various object types.

Cross-object Type Consistency

Maintains consistent samurai transformation effects whether the subject is a person or an animal.

Simple Prompt Structure

Provides easy-to-adjust prompt templates for quick user onboarding.

Community Support

Offers Discord community support where users can freely use LoRA to generate videos and submit training requests.

Model Capabilities

Image-to-video

Text-to-video

LoRA fine-tuning

Samurai effects generation

Use Cases

Entertainment

Human Samurai Transformation

Converts ordinary human images into samurai versions, generating transformation videos.

example_videos/man_samurai.mp4

Animal Samurai Transformation

Transforms animal images into samurai versions, creating fun transformation videos.

example_videos/rabbit_samurai.mp4

🚀 Samurai Effect LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling any person or object in an image to transform into a samurai version of themselves!

✨ Features

Transform any image into a video of the subject as a Samurai version of themselves!
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!

📦 Installation

📥 Download Links:

samurai_50_epochs.safetensors - LoRA Model File
wan_I2V_LoRA_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

📚 Documentation

⚙️ Recommended Settings

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;"> 54mur41 samurai transformation</code>

📝 Prompt Template

For best results, try following the structure of the prompt examples above. These worked well for me.

🔧 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. See the Downloads section above for the modified workflow.

🔧 Technical Details

📋 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 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a Samurai!
Epochs	50

🛠️ 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