metadata

license: apache-2.0
language:
  - en
base_model:
  - Wan-AI/Wan2.1-I2V-14B-480P
  - Wan-AI/Wan2.1-I2V-14B-480P-Diffusers
pipeline_tag: image-to-video
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
  - image-to-video
widget:
  - text: >-
      The video begins with a close-up portrait of a man wearing a suit. The
      background changes and then the pu11y puppy effect begins. The man is now
      surrounded by many puppies. He pets the puppies. 
    output:
      url: example_videos/man1_puppy.mp4
  - text: >-
      The video begins with a relaxed shot of a man smiling, sitting on a modern
      gray armchair. The pu11y puppy effect happens, and the man is surrounded
      by golden retriever puppies. He interacts with the puppies on his phone.
    output:
      url: example_videos/man2_puppy.mp4
  - text: >-
      The video opens with a studio portrait of a man smiling in a white
      t-shirt. The pu11y puppy effect then begins, as puppies begin to gather
      and surround him. He is now holding a puppy in his arms.
    output:
      url: example_videos/man3_puppy.mp4

Puppy 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 get surrounded by puppies!

Features

Transform any image into a video of the subject surrounded by puppies!
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 close-up portrait of a man wearing a suit. The background changes and then the pu11y puppy effect begins. The man is now surrounded by many puppies. He pets the puppies.

Prompt: The video begins with a relaxed shot of a man smiling, sitting on a modern gray armchair. The pu11y puppy effect happens, and the man is surrounded by golden retriever puppies. He interacts with the puppies on his phone.

Prompt: The video opens with a studio portrait of a man smiling in a white t-shirt. The pu11y puppy effect then begins, as puppies begin to gather and surround him. He is now holding a puppy in his arms.

Model File and Inference Workflow

📥 Download Links:

puppy_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: pu11y puppy effect

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 getting surrounded by puppies!
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!