Historic Painting 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 historic painting version of themselves!

Features

• Transform any image into a video of the subject as a historic painting 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 starts with a dog. The next scene shows the dog inside a gold framed mirror in a room. The dog is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the dog transforms into a p41nt1ng painting frame it, where the dog is dressed in red and blue clothing. The background is an older style painting scene. Finally, the dog is in another p41nt1ng painting frame it, where it is dressed in a red robe with the same landscape background in the painting.

Prompt

The video starts with a woman. The next scene shows the woman inside a gold framed mirror in a room. She is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the woman transforms into a p41nt1ng painting frame it, where she is dressed in red and blue clothing. The background is an older style painting scene. Finally, the woman is in another p41nt1ng painting frame it, where she is dressed in a red robe with the same landscape background in the painting.

Prompt

The video starts with a man. The next scene shows the man inside a gold framed mirror in a room. He is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the man transforms into a p41nt1ng painting frame it, where he is dressed in red and blue clothing. The background is an older style painting scene. Finally, the man is in another p41nt1ng painting frame it, where he is dressed in a red robe with the same landscape background in the painting.

Model File and Inference Workflow

📥 Download Links:

• painting_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: p41nt1ng painting frame it

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 painting 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!