Crush Open-Source Image Special Effects Model - Free Convert Image Objects into Video Effects of Being Crushed by a Hydraulic Press

Crush

Developed by Remade-AI

A LoRA trained on the Wan2.1 14B I2V 480p model, capable of transforming any object in an image into a video effect of being crushed by a hydraulic press

Text-to-Video EnglishOpen Source License:Apache-2.0 #Hydraulic Press Crushing Effect #Image-to-Video #LoRA Fine-tuning

Downloads 1,830

Release Time : 3/11/2025

Model Overview

This LoRA model is specifically designed to generate video effects of objects being crushed, suitable for various objects (animals, vehicles, people, etc.), producing realistic crushing effect videos with simple text prompts.

Model Features

Universal Object Crushing Effect

Applicable to various objects, from animals and vehicles to people, presenting consistent crushing effects

Simple Prompt Structure

Uses standardized prompt templates; simply replace the object noun to generate different crushing videos

High-Quality Video Output

Trained on the Wan2.1 14B 480p I2V base model, maintaining 480p video quality

Community Support

Provides Discord community support, allowing free generation of special effect videos and submission of LoRA training requests

Model Capabilities

Text-to-Video Generation

Image-to-Video Conversion

Special Effect Video Generation

LoRA Fine-tuning Adaptation

Use Cases

Special Effect Video Production

Tank Crushing Effect

Generate a video of a tank being crushed and deformed by a hydraulic press

example_videos/tank_crush.mp4

Human Crushing Effect

Generate a video of a person being crushed and deformed by a hydraulic press

example_videos/man_crush.mp4

Object Crushing Effect

Generate videos of various everyday objects (e.g., soda cans) being crushed

example_videos/coke_crush.mp4

Creative Content Generation

Special Effect Production

Create special crushing effect materials for films, games, etc.

🚀 Crush Effect LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling you to create videos where any object in an image gets crushed.

🚀 Quick Start

This LoRA allows you to transform any image into a video of the object being crushed. You can download the necessary model file and workflow, and follow the recommended settings and prompt templates to generate videos.

✨ Features

Video Transformation: Transform any image into a video of it being crushed.
Base Model Compatibility: Trained on the Wan2.1 14B 480p I2V base model.
Consistent Results: Deliver consistent results across different object types.
Simple Prompt Structure: Use a simple prompt structure that's easy to adapt.

📦 Installation

📥 Download Links

crush_20_epochs.safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

📚 Documentation

Recommended Settings

Property	Details
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;"> c5us4 crushes it</code>

Prompt Template

For best results, use this prompt structure:

The video begins with a [object]. A hydraulic press positioned above slowly descends towards the [object]. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the [object], causing the [object] to collapse inward until the [object] is no longer recognizable.

Simply replace <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">[object]</code> with whatever you want to see crushed!

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 I2V 480p
Training Data	Trained on 1.5 minutes of video comprised of 20 short clips (each clip captioned separately) of things being crushed by a hydraulic press
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!

📄 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