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

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to cakeify any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

Features

• Transform any image into a video of it being cakeified
• 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 on a puppy. A knife, held by a hand, is coming into frame and hovering over the puppy. The knife then begins cutting into the puppy to c4k3 cakeify it. As the knife slices the puppy open, the inside of the puppy is revealed to be cake with chocolate layers. The knife cuts through and the contents of the puppy are revealed.

Prompt

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

Prompt

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

Prompt

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

Model File and Inference Workflow

📥 Download Links:

• cakeify_16_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: 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.

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: 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!