Princess 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 become a princess version of themselves!

Features

• Transform any image into a video of the subject as a princess version of themselves!
• 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 begins with an image of a woman. A pr1nc355 princess transformation then happens as white sparkling light appears around the woman's shoulders and chest. The woman is now wearing a tiara on her head, a long, silver beaded gown, and silver gloves that reach up to her biceps. The woman is seated on a chair in front of a table with gifts and candles. The background is a room with white curtains. The woman is looking directly at the camera and holding her hand up. The camera pans to the right to display more gifts and candles. Thew man then moves their hand closer to the camera.

Prompt

The video begins with an image of a man. A pr1nc355 princess transformation then happens as white sparkling light appears around the man's shoulders and chest. The man is now wearing a tiara on his head, a long, silver beaded gown, and silver gloves that reach up to their biceps. The man is seated on a chair in front of a table with gifts and candles. The background is a room with white curtains. The man is looking directly at the camera and holding their hand up. The camera pans to the right to display more gifts and candles. The man then moves their hand closer to the camera.

Model File and Inference Workflow

📥 Download Links:

• princess_45_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: pr1nc355 princess transformation

Prompt Template

For best results, try following the structure of the prompt examples above. These worked well for me.

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 transforming into a princess!
• Epochs: 45

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!