Zen

Developed by Remade-AI

LoRA trained on Wan2.1 14B I2V 480p model that transforms any person/object in images into zen versions and generates videos.

Text-to-Video EnglishOpen Source License:Apache-2.0 #Image-to-Video #Zen Effects #LoRA Fine-tuning

Downloads 544

Release Time : 3/15/2025

Model Overview

This model achieves image-to-video conversion through LoRA technology, specializing in transforming subjects into zen style and generating coherent metamorphosis videos.

Model Features

Zen Style Transformation

Transforms any image subject into zen style and generates metamorphosis videos

Cross-Object Consistency

Maintains consistent style transformation effects across different object types

Simple Prompt Structure

Achieves good results using standardized prompt templates

Community Support

Provides Discord community support and accepts free LoRA training requests

Model Capabilities

Image style transfer

Video generation

Cross-modal conversion

Zen effects application

Use Cases

Creative Content Generation

Character Zen Metamorphosis

Transforms human or fictional characters into zen style and generates metamorphosis videos

example_videos/thanos_zen.mp4

Animal Effects Videos

Adds zen effects to animals and generates stylized videos

example_videos/rodent_zen.mp4

Artistic Creation

Stylized Short Video Generation

Quickly generates short video content with unified artistic style

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 starts with a portrait of a rodent. The scene then transitions to the rodent's z3n1fy zen transformation as the rodent is wearing a pink robe with a white shirt underneath, with a zen garden background. The rodent is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed rodent, in what appears to be a garden setting. The rodent is now wearing a black kimono with white floral designs and a white belt. The rodent carries a basket in one hand and a colorful fan in the other. The rodent is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. The rodent has a neutral expression, looking directly at the camera. output: url: example_videos/rodent_zen.mp4
text: >- The video starts with a portrait of a purple Thanos from Marvel. The scene then transitions to the Thanos' z3n1fy zen transformation as he's wearing a pink robe with a white shirt underneath, with a zen garden background. Thanos is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed Thanos, in what appears to be a garden setting. He is now wearing a black kimono with white floral designs and a white belt. Thanos carries a basket in one hand and a colorful fan in the other. He is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. Thanos has a neutral expression, looking directly at the camera. output: url: example_videos/thanos_zen.mp4
text: >- The video starts with a portrait of an old man. The scene then transitions to the man's z3n1fy zen transformation as he's wearing a pink robe with a white shirt underneath, with a zen garden background. He is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed man, in what appears to be a garden setting. He is now wearing a black kimono with white floral designs and a white belt. He carries a basket in one hand and a colorful fan in the other. He is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. The man has a neutral expression, looking directly at the camera. output: url: example_videos/man_zen.mp4

Zen 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 Zen version of themselves!

Features

Transform any image into a video of the subject as a Zen 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!

Model File and Inference Workflow

📥 Download Links:

zen_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: z3n1fy zen transformation

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 their zen version!
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