Cakeify Open Source Model - Free to Convert Any Image Object into a Cake-shaped Special Effects Video

Cakeify

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 cake-effect video

Video Processing EnglishOpen Source License:Apache-2.0 #Image Cake Transformation #Dynamic Cutting Effects #LoRA Fine-tuned Model

Downloads 1,955

Release Time : 3/11/2025

Model Overview

This model extends the functionality of the base image-to-video model through LoRA technology, specializing in generating videos with 'cakeified' effects, showcasing the process of objects transforming into cake structures internally.

Model Features

Cross-object Cake Effect

Transforms various objects such as animals, people, and items into cake forms while maintaining effect consistency

Dynamic Cutting Process

Simulates the process of cutting objects with a knife and reveals the complete dynamic transformation into cake structures

Simple Prompt Structure

Provides standardized prompt templates where only the object name needs to be replaced to generate effect videos

LoRA Adaptation Technology

As a lightweight adapter, it can flexibly enable/disable cake effects on the base model

Model Capabilities

Image-to-video conversion

Special effects video generation

Object form transformation

Dynamic process simulation

Use Cases

Creative Video Production

Animal Cake Effect

Transforms animals like puppies into cake-form videos

Example Video/Puppy Cake.mp4

Human Cake Effect

Transforms people into cake-form videos

Example Video/Woman Cake.mp4

Item Cake Effect

Transforms items like boots into cake-form videos

Example Video/Timberland Cake.mp4

Educational Demonstration

Object Structure Display

Visually demonstrates internal object structures through the cake transformation process

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

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling you to transform any object in an image into a cake - themed video. It offers consistent results across various object types and has a simple prompt structure.

✨ Features

Transform any image into a video of it being cakeified.
Trained on the Wan2.1 14B 480p I2V base model.
Deliver consistent results across different object types.
Feature a simple prompt structure that's easy to adapt.

📦 Installation

📥 Download Links:

cakeify_16_epochs.safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V 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: c4k3 cakeify it

Prompt Template

For best results, use this prompt structure:

The video opens on a [object]. A knife, held by a hand, is coming into frame and hovering over the [object]. The knife then begins cutting into the [object] to c4k3 cakeify it. As the knife slices the [object] open, the inside of the [object] is revealed to be cake with chocolate layers. The knife cuts through and the contents of the [object] are revealed.

Simply replace [object] with whatever you want to see cakeified!

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	1 minute of video (13 short clips of things being cakeified, each clip captioned separately)
Epochs	16

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!

👥 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!

📄 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