VIP Red Carpet 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 female VIP version of themselves!

Features

• Transform any image into a video of the subject as a female VIP 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 purple Thanos from Marvel. Then the v1p red carpet transformation appears. Purple Thanos is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of purple Thanos looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, purple Thanos is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. Purple Thanos is wearing the same black dress and jewelry, in focus at the center of the frame.

Prompt

The video begins with an image of a man. Then the v1p red carpet transformation appears. He is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of him looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, he is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. He is wearing the same black dress and jewelry, in focus at the center of the frame.

Model File and Inference Workflow

📥 Download Links:

• vip_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: v1p red carpet 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 female VIP version of themselves!
• 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!