Tsunami Open-Source Text-to-Video Model - Free Experience of Generating Realistic Tsunami Scene Videos

Tsunami

Developed by Remade-AI

LoRA trained on the Wan2.1 14B text-to-video model, specialized for generating realistic tsunami scene videos

Text-to-Video EnglishOpen Source License:Apache-2.0 #Tsunami scene generation #Disaster simulation video #LoRA fine-tuning

Downloads 62

Release Time : 3/20/2025

Model Overview

This LoRA model can generate high-quality tsunami scene videos based on text prompts, including details such as wave impacts and building destruction

Model Features

Realistic tsunami scene generation

Capable of generating realistic tsunami scenes, including details like wave impacts and building destruction

Multi-scene adaptability

Maintains stable generation performance across different objects and scene types

Simple prompt control

Provides easy-to-adjust simple prompt templates for user control over generated content

Model Capabilities

Text-to-video generation

Specific scene video generation

Natural disaster simulation

Use Cases

Film special effects

Disaster scene production

Used for tsunami scene effects in movies and TV shows

Generates realistic tsunami impact scenes

Educational demonstrations

Natural disaster teaching

Used in geography courses to demonstrate tsunami formation and impact

Generates tsunami simulation videos of different intensities

🚀 Realistic Tsunami LoRA for Wan2.1 14B T2V

This LoRA model is trained on the Wan2.1 14B T2V model, enabling users to generate videos of realistic tsunamis. It offers consistent results across various object and scene types and comes with simple, adaptable prompt examples.

✨ Features

Trained on the Wan2.1 14B T2V base model.
Provides consistent results across different object and scenes types.
Offers 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!

📦 Installation

📥 Download Links

tsunami_4_epochs.safetensors - LoRA Model File
wan_txt2vid_lora_workflow.json - Wan T2V with LoRA Workflow for ComfyUI

📚 Documentation

⚙️ Recommended Settings

LoRA Strength: 1.0
Embedded Guidance Scale: 6.0
Flow Shift: 5.0

🔑 Trigger Words

The key trigger phrase is: <code style="background - color: #f0f0f0; padding: 3px 6px; border - radius: 4px;">t5un@m1 realistic tsunami</code>

📝 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.

Workflow Screenshot

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

Property	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!

📄 License

This project is licensed under the Apache - 2.0 license.

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