Jungle

Developed by Remade-AI

LoRA trained on Wan2.1 14B I2V 480p model, capable of transforming characters/objects in images into jungle-style dynamic videos

Text-to-Video EnglishOpen Source License:Apache-2.0 #Jungle style transformation #Dynamic video generation #LoRA fine-tuning

Downloads 417

Release Time : 3/15/2025

Model Overview

This model achieves image-to-video conversion through LoRA technology, specializing in transforming ordinary portraits into dynamic jungle Tarzan-style scenes while maintaining effect consistency across different object types.

Model Features

Jungle style transformation

Convert any image into dynamic jungle Tarzan-style videos

Cross-object consistency

Maintain consistent transformation effects across different types of characters/objects

Simple prompt structure

Achieve high-quality results through standardized prompt templates

ComfyUI integration

Provides dedicated workflow files compatible with Kijai's Wan video wrapper tool

Model Capabilities

Image-to-video conversion

Stylized transformation

Dynamic scene generation

LoRA fine-tuning application

Use Cases

Creative content generation

Jungle adventure video generation

Transform ordinary portraits into dynamic jungle adventure-themed videos

Example video shows the dynamic process of characters transforming into jungle warriors

Stylized short video creation

Quickly generate short videos with unified styles for social media

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 portrait of a man. The background is blurry, with shades of grey and green. Next, the 1ung13 jungle transformation occurs. The man is now in a jungle setting, bathed in sunlight. His hair is longer, and his hair is up. He is shirtless, with tribal markings on his chest. He wears jungle-like shorts. The man is swinging from a vine, posing in a dynamic, action-oriented manner. A dark panther-like figure is in the background. The scene evokes a sense of adventure and the wild. output: url: example_videos/man2_jungle.mp4
text: >- The video begins with a portrait of a man. The background is blurry, with shades of grey and green. Next, the 1ung13 jungle transformation occurs. The man is now in a jungle setting, bathed in sunlight. His hair is longer, and his hair is up. He is shirtless, with tribal markings on his chest. He wears jungle-like shorts. The man is swinging from a vine, posing in a dynamic, action-oriented manner. A dark panther-like figure is in the background. The scene evokes a sense of adventure and the wild. output: url: example_videos/man1_jungle.mp4

Jungle 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 jungle version of themselves!

Features

Transform any image into a video of the subject as a jungle Tarzan 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:

jungle_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: 1ung13 jungle 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 jungle 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