metadata

license: apache-2.0
language:
  - en
base_model:
  - Wan-AI/Wan2.1-T2V-14B
pipeline_tag: text-to-video
tags:
  - text-to-video
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: >-
      The video shows a coastal village hit by a t5un@m1 realistic tsunami.
      Buildings are flooded, boats are capsized, and debris litters the streets,
      while people are seen evacuating the area.
    output:
      url: example_videos/tsunami1.mp4
  - text: >-
      The video is of a beach with many boats and jet skis. The water recedes
      and then a t5un@m1 realistic tsunami rushes in, sweeping away all the
      objects on the beach. The sky is sunny.
    output:
      url: example_videos/tsunami2.mp4
  - text: >-
      The video shows a t5un@m1 realistic tsunami wave crashing into a coastal
      area. The wave is large and powerful, and it destroys everything in its
      path. There are several boats and buildings in the path of the wave. The
      water is a murky brown color.
    output:
      url: example_videos/tsunami3.mp4
  - text: >-
      The video shows a coastal city after a t5un@m1 realistic tsunami. The city
      is flooded with water, and there are many damaged buildings and cars. The
      sky is a dark gray.
    output:
      url: example_videos/tsunami4.mp4

Realistic Tsunami LoRA for Wan2.1 14B T2V

Overview

This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos of realistic tsunamis!

Features

Trained on the Wan2.1 14B T2V base model
Consistent results across different object and scenes types
Simple prompt examples that are 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 shows a coastal village hit by a t5un@m1 realistic tsunami. Buildings are flooded, boats are capsized, and debris litters the streets, while people are seen evacuating the area.

Prompt: The video is of a beach with many boats and jet skis. The water recedes and then a t5un@m1 realistic tsunami rushes in, sweeping away all the objects on the beach. The sky is sunny.

Prompt: The video shows a t5un@m1 realistic tsunami wave crashing into a coastal area. The wave is large and powerful, and it destroys everything in its path. There are several boats and buildings in the path of the wave. The water is a murky brown color.

Prompt: The video shows a coastal city after a t5un@m1 realistic tsunami. The city is flooded with water, and there are many damaged buildings and cars. The sky is a dark gray.

Model File and Inference Workflow

📥 Download Links:

tsunami_4_epochs.safetensors - LoRA Model File
wan_txt2vid_lora_workflow.json - Wan T2V 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: t5un@m1 realistic tsunami

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 T2V
Training Data: Trained on 6 minutes of video comprised of 74 short clips (each clip captioned separately) of various real tsunami videos.
Epochs: 4

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!