Explosion LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to generate videos of an explosion in any scene! This model also works on T2V, with a very similar prompting style.

Features

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: The video opens with a close-up of a smiling man, with curly hair, in a light-colored sweater. The man is smiling and looking up. The man is in front of a background with green hills and a bright sky. Then, the face of the smiling man 3xp105ion huge explosion that engulfs the entire screen with a bright light. The light is so bright that it obscures the man and his surroundings.

Prompt: The video shows a close-up of a 3xp105ion huge explosion on a snowy mountain, with ice and snow being thrown into the air.

Prompt: The video shows a 3xp105ion huge explosion in the middle of the ocean, creating a massive wave of water and a huge cloud of steam.

Prompt: The video opens on a grassy field, with a large 3xp105ion huge explosion sending debris and smoke high into the air.

Model File and Inference Workflow

📥 Download Links:

explode_30_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: 3xp105ion huge explosion

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 56 seconds of video comprised of 16 short clips (each clip captioned separately) of various explosions
Epochs: 30

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!

Remade-AI
/

Explode