Remade-AI/Pirate-Captain

Pirate Captain 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 Pirate Captain version of themselves!

Features

• Transform any image into a video of the subject as a Pirate Captain 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 a cat. The image then transitions to the p1r4t3 pirate captain transformation. The cat is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the cat on a wooden ship. The cat has long dreadlock style hair and a sword. The scene changes again to show the cat with his sword, in the same location on the boat.

Prompt

The video begins with Goku. The image then transitions to the p1r4t3 pirate captain transformation. Goku is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing Goku on a wooden ship. Goku has long dreadlock style hair and a sword. The scene changes again to show Goku with his sword, in the same location on the boat.

Prompt

The video begins with a man posing. The image then transitions to the p1r4t3 pirate captain transformation. The man is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the man on a wooden ship. He has long dreadlock style hair and a sword. The scene changes again to show the man with his sword, in the same location on the boat.

Prompt

The video begins with a rabbit. The image then transitions to the p1r4t3 pirate captain transformation. The rabbit is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the rabbit on a wooden ship. The rabbit has long dreadlock style hair and a sword. The scene changes again to show the rabbit with his sword, in the same location on the boat.

Model File and Inference Workflow

📥 Download Links:

• pirate_captain_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: p1r4t3 pirate captain 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 pirate captain!
• 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!