Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.

Join our Discord to generate videos of the Cakeify Effect LoRA for free.

Wan2.1 14B I2V 480p v1.0:

Trained on 1 minute of video comprised of 13 short clips of things being cakeified. This was trained on the Wan.21 14B I2V 480p model.

The trigger word is: 'c4k3 cakeify it'

See below for the prompt structure that's worked best for me. The only difference between prompts would be the object being cakeified!

Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 6.0

Flow shift = 5.0

Here's a link to the Wan2.1 I2V LoRA inference workflow I used to generate these videos: https://huggingface.co/Remade/Squish/blob/main/workflow/wan_img2video_lora_workflow.json

This is a slight modification to Kijai's version, with the main difference being the addition of the WanVideo Lora Select node, connected to the 'lora' field of the WanVideo Lora Select node. Find Kijai's original workflow here:
https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_480p_I2V_example_02.json

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.

Let me know if there are any questions, I'll be happy to help!