Remade-AI/Hug-Jesus

Hug Jesus LoRA for Wan2.1 14B I2V 480p

Overview

This LoRA is trained on the Wan2.1 14B I2V 480p model and makes Jesus hug any object in an image. The effect works on a wide variety of objects, from animals to people!

Features

• Transform any image into a video of Jesus hugging the image subject
• Trained on the Wan2.1 14B 480p I2V base model
• Consistent results across different object types
• Simple prompt examples that are 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

A studio portrait of a young black man is smiling at the camera while in a bright mustard-yellow t-shirt. He is holding the face of Jesus. Then, h54g hugs jesus in a loving embrace as they are smiling. The background subtly changes as they begin to hug.

Prompt

A close-up portrait of a young woman is presented, with her eyes, smiling. Then, Jesus appears and embraces the woman. h54g hugs jesus and they are both smiling.

Prompt

The video features a close-up of a tabby cat lying down. Then, a smiling Jesus appears behind the cat, and he hugs the cat. The cat and Jesus are hugging.

Prompt

The video begins with Pepe the Frog, his eyes slowly looking around, then the mouth starts to subtly twitch as he looks at a light blue backdrop. Suddenly, Jesus appears behind him, and his face changes, and he begins to show emotion. The two begin to look at each other and h54g hugs jesus, while smiling.

Model File and Inference Workflow

📥 Download Links:

• hug_jesus_20_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: h54g hugs jesus

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 8 short clips (each clip captioned separately) of people hugging Jesus
• Epochs: 20

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!