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

Overview

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

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

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!

Prompt

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.

Prompt

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.

Prompt

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.

Prompt

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.

Model File and Inference Workflow

📥 Download Links:

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

---

Recommended Settings

• 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

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.

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

• 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

Acknowledgments

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