Remade-AI/Gun-Shooting

Gun Shooting Effect LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image shoot a gun. The effect works on a wide variety of objects, from animals to people!

Features

• Transform any image into a video of the subject pulling out and shooting a gun
• 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

Luffy looks intently off-camera and the camera zooms out as Luffy p5lls g4un pulls a gun and starts shooting.

Prompt

Neymar looks intently off-camera in the rain, rain drops begin to fall and the camera zooms out as he p5lls g4un pulls a gun and starts shooting.

Prompt

A rodent looks intently off-camera and the camera zooms out as the rodent p5lls g4un pulls a gun and starts shooting.

Prompt

A woman looks intently off-camera and the camera zooms out as she p5lls g4un pulls a gun and starts shooting.

Model File and Inference Workflow

📥 Download Links:

• gun_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: p5lls g4un pulls a gun and starts shooting.

Prompt Template

For best results, use this prompt structure:

A [object] looks intently off-camera and the camera zooms out as the [object] p5lls g4un pulls a gun and starts shooting.

Simply replace [object] with whatever you want to see pulling a gun out and shooting!

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 1 minute of video comprised of 10 short clips (each clip captioned separately) of people pulling up a gun and starting to shoot
• 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!