Remade-AI/Selfie-With-Younger-Self

Taking a Selfie with Your Younger Self LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to take a selfie with your younger self!

Features

• 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 man with a beard smiling at the camera, then s31lf13 taking a selfie with their younger self, and the younger self appears next to him with similar facial features and eye color. The younger self wears a white t-shirt and has a cream white jacket. The younger self is smiling slightly.

Prompt

The video shows a man with gray hair, wearing a gray shirt and smiling at the camera. Then, s31lf13 taking a selfie with their younger self, the younger self shares similar facial features. The younger self is smiling. The two are in the s31lf13 taking a selfie with their younger self.

Prompt

The video shows a woman with black skin, dark hair, and dark eyes who is smiling as she looks towards the camera. Then, s31lf13 taking a selfie with their younger self, her younger self then appears next to her. The younger self shares similar facial features, eye colour and skin tone appearing to be the woman when she was young.

Model File and Inference Workflow

📥 Download Links:

• selfie_younger_self_15_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: s31lf13 taking a selfie with their younger self

Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

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 40 seconds of video comprised of 9 short clips (each clip captioned separately) of people taking a selfie with their younger self
• Epochs: 35

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!