Open-source Fus-Ro-Dah Model - Convert Images to Spell Impact Video Effects for Free

Fus Ro Dah

Developed by Remade-AI

LoRA trained on the Wan2.1 14B I2V 480p model, capable of transforming images into videos with Fus-Ro-Dah spell impact effects

Video Processing EnglishOpen Source License:Apache-2.0 #Game Effect Generation #Dynamic Shockwave Effect #Image-to-Video LoRA

Downloads 113

Release Time : 3/20/2025

Model Overview

This LoRA model is specifically designed for image-to-video tasks, applying the Fus-Ro-Dah spell effect from 'The Elder Scrolls' game to any object in an image, generating dynamic videos of objects being blasted away by shockwaves.

Model Features

Fus-Ro-Dah Spell Effect

Transforms any object in an image into a video with Fus-Ro-Dah spell impact effects

Multi-Object Applicability

Effective for various objects including characters, animals, vehicles, and other types

Simple Prompt Structure

Provides standardized prompt templates to simplify the usage process

Community Support

Offers Discord community support, free to use and submit LoRA training requests

Model Capabilities

Image-to-Video

Special Effects Generation

Dynamic Effect Rendering

Use Cases

Game Effects

Character Blasting Effect

Generates dynamic effects of game characters being blasted away by Fus-Ro-Dah spells

example_videos/fus2.mp4

Monster Knockback Effect

Generates animations of game monsters being repelled by spell shockwaves

example_videos/fus3.mp4

Creative Videos

Object Dynamic Effects

Adds shockwave blasting effects to objects in static images

example_videos/fus1.mp4

Vehicle Special Effects

Generates exaggerated effects of vehicles being blasted away by shockwaves

example_videos/fus4.mp4

🚀 Skyrim Fus-Ro-Dah LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model. It allows you to apply the Fus - Ro - Dah spell on any object in an image. The effect can be applied to a wide variety of objects, including animals, vehicles, and people.

🚀 Quick Start

Download

fus_ro_dah_20_epochs.safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

Recommended Settings

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

Trigger Words

The key trigger phrase is: fus_r0_d4h force push effect

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

✨ Features

Transform any image into a video of it taking on a Fus - Ro - Dah spell!
Trained on the Wan2.1 14B 480p I2V base model
Consistent results across different object types
Simple prompt structure that's easy to adapt

📚 Documentation

Prompt Template

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

Example Prompts

A large man on a white donkey trots across a desert, kicking up dust, then is suddenly flung backwards by the fus_r0_d4h force push effect, flying over a utility pole and into the sky. Output Video
A knight is charging forward, and then he is hit by a fus_r0_d4h force push effect and sent flying backward into a wall. Output Video
A fearsome hybrid creature stands in murky water, then is flung backwards by the fus_r0_d4h force push effect, and disappearing into the swamp. Output Video
A tank moves across a desert landscape, kicks up a dust cloud, then suddenly experiences the fus_r0_d4h force push effect, being flung backward over low hills and into the sky. Output Video

🔧 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 2 minutes of video comprised of 32 short clips (each clip captioned separately) of the Fus - Ro - Dah effect in action!
Epochs	20

Additional Information

Training was done using Diffusion Pipe for Training

📄 License

This project is licensed under the Apache - 2.0 license.

🌟 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!

🙏 Acknowledgments

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

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