kissing Open-source Image-to-Video Model - Freely Generate Kissing Interaction Effects

Kissing

Developed by Remade-AI

LoRA trained on the Wan2.1 14B I2V 480p model for generating kissing interaction videos from images

Video Processing EnglishOpen Source License:Apache-2.0 #Image-to-Video #Kissing Motion Generation #LoRA Fine-tuning

Downloads 686

Release Time : 4/1/2025

Model Overview

This is a specialized LoRA model for generating kissing interaction videos, based on the Wan2.1 14B image-to-video 480p version, capable of maintaining effect consistency across different object types.

Model Features

Cross-Object Type Consistency

Maintains kissing effect consistency across different character types

Simple Prompt Structure

Achieves good results using standardized prompt templates

Community Support

Provides Discord community support for submitting LoRA training requests

Model Capabilities

Image-to-video generation

Specific motion generation (kissing)

Character interaction scene generation

Use Cases

Film Production

Romantic Scene Generation

Generate romantic kissing scenes for movies or TV shows

Can produce kissing interaction videos in various environments

Game Development

Character Interaction Animation

Generate kissing interaction animations for game characters

Customizable kissing animations for different character appearances and scenes

🚀 Kissing LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling users to generate videos of people kissing.

🚀 Quick Start

Model Information

Property	Details
Model Type	LoRA for image - to - video
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 Examples

Prompt 1: A man and a woman wearing jackets and hats are standing close together in the snowy mountains. The man is standing facing the woman, then they engage in k144ing kissing.
- Output: example_videos/1.mp4
Prompt 2: A man with a beard is shown smiling. A woman comes into the scene and starts passionately k144ing kissing the man.
- Output: example_videos/2.mp4
Prompt 3: A man and a woman are embracing near a lake with mountains in the background. They are k144ing kissing, while still embracing each other.
- Output: example_videos/3.mp4

✨ Features

Trained on the Wan2.1 14B 480p I2V base model.
Consistent results across different object types.
Simple prompt structure that's easy to adapt.

📦 Installation

📥 Download Links

kissing_30_epochs..safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

📚 Documentation

Recommended Settings

LoRA Strength: 1.0
Embedded Guidance Scale: 6.0
Flow Shift: 5.0

Trigger Words

The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;"> k144ing kissing</code>

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.

Workflow Screenshot

See the Downloads section above for the modified workflow.

Training Details

Base Model: Wan2.1 14B I2V 480p
Training Data: Trained on 50 seconds of video comprised of 11 short clips (each clip captioned separately) of people kissing.
Epochs: 30

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!

📄 License

This project is licensed under the Apache - 2.0 license.

🌐 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!

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