Baby 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 make any person/object in an image into a baby!

Features

• Transform any image into a video of the subject as a baby!
• 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 starts with a studio portrait of Goku. Then the image shifts to the 848y baby effect, Goku is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of Goku is in the crib and seems excited and amused.

Prompt

The video starts with a studio portrait of an Asian man. Then the image shifts to the 848y baby effect, the man is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the man is in the crib and seems excited and amused.

Prompt

The video starts with a studio portrait of a woman. Then the image shifts to the 848y baby effect, the woman is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the woman is in the crib and seems excited and amused.

Model File and Inference Workflow

📥 Download Links:

• baby_50_epochs.safetensors - LoRA Model File
• wan_I2V_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: 848y baby effect

Prompt Template

For best results, use this prompt structure:

The video starts with a studio portrait of a [object]. Then the image shifts to the 848y baby effect, the [object] is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the [object] is in the crib and seems excited and amused.

Simply replace [object] with whatever you want to see as a baby!

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: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people becoming a baby!
• Epochs: 50

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!