Puppy

Developed by Remade-AI

A fine-tuned model based on Wan2.1 14B I2V 480p, capable of adding puppy surround effects to any person/object in images

Video Processing EnglishOpen Source License:Apache-2.0 #Image-to-Video #Puppy Surround Effect #Character Animation

Downloads 562

Release Time : 3/14/2025

Model Overview

This model transforms static images into dynamic videos where target objects are surrounded by puppies. It is trained on the Wan2.1 14B 480p image-to-video base model, ensuring consistent effects across different object types.

Model Features

Puppy Surround Effect

Adds dynamic puppy surround effects to any person or object in images

Powerful Base Model

Trained on Wan2.1 14B 480p image-to-video base model, ensuring high-quality video generation

Consistent Effects

Maintains consistent puppy surround effects across different target objects

Easy to Use

Provides simple and adjustable prompt structures for quick user adoption

Model Capabilities

Image-to-Video

Effect Addition

Dynamic Video Generation

Use Cases

Entertainment Applications

Character Effect Videos

Adds dynamic puppy surround effects to portraits

Generates fun videos of characters interacting with puppies

Object Effect Videos

Adds dynamic puppy surround effects to specific objects

Generates fun videos of objects surrounded by puppies

Social Media Content Creation

Fun Short Video Production

Quickly creates short videos with puppy effects

Generates fun videos suitable for social media sharing

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!

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!

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご