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 starts with a man. The next scene shows him with a mountain
      range in the background. His shirt is pulled up to his midriff, and he is
      wearing a skirt-like bottom. The man has a belt around his waist and is
      gesturing with his right hand. He is wearing brown, medieval looking
      leggings. The effect seen is warr10r warrior it. The man now appears as a
      warrior with an axe. He is shirtless, muscular, has tattoos, and is
      smiling with a determined look on his face. The background is the same
      mountain range as before. The next scene shows the man still as a warrior,
      and he is holding an axe with a golden axe head.
    output:
      url: example_videos/man1_warrior.mp4
  - text: >-
      The video starts with a man. The next scene shows him with a mountain
      range in the background. His shirt is pulled up to his midriff, and he is
      wearing a skirt-like bottom. The man has a belt around his waist and is
      gesturing with his right hand. He is wearing brown, medieval looking
      leggings. The effect seen is warr10r warrior it. The man now appears as a
      warrior with an axe. He is shirtless, muscular, has tattoos, and is
      smiling with a determined look on his face. The background is the same
      mountain range as before. The next scene shows the man still as a warrior,
      and he is holding an axe with a golden axe head.
    output:
      url: example_videos/man2_warrior.mp4
  - text: >-
      The video starts with a dog. The next scene shows the dog with a mountain
      range in the background. The dog's shirt is pulled up to his midriff, and
      it is wearing a skirt-like bottom. The dog has a belt around its waist and
      is gesturing with its right hand. The dog is wearing brown, medieval
      looking leggings. The effect seen is warr10r warrior it. The dog now
      appears as a warrior with an axe. The dog is shirtless, muscular, has
      tattoos, and is smiling with a determined look on her face. The background
      is the same mountain range as before. The next scene shows the dog still
      as a warrior, and he is holding an axe with a golden axe head.
    output:
      url: example_videos/dog_warrior.mp4

Warrior 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 warrior version of themselves!

Features

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

Prompt: The video starts with a man. The next scene shows him with a mountain range in the background. His shirt is pulled up to his midriff, and he is wearing a skirt-like bottom. The man has a belt around his waist and is gesturing with his right hand. He is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The man now appears as a warrior with an axe. He is shirtless, muscular, has tattoos, and is smiling with a determined look on his face. The background is the same mountain range as before. The next scene shows the man still as a warrior, and he is holding an axe with a golden axe head.

Prompt: The video starts with a man. The next scene shows him with a mountain range in the background. His shirt is pulled up to his midriff, and he is wearing a skirt-like bottom. The man has a belt around his waist and is gesturing with his right hand. He is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The man now appears as a warrior with an axe. He is shirtless, muscular, has tattoos, and is smiling with a determined look on his face. The background is the same mountain range as before. The next scene shows the man still as a warrior, and he is holding an axe with a golden axe head.

Prompt: The video starts with a dog. The next scene shows the dog with a mountain range in the background. The dog's shirt is pulled up to his midriff, and it is wearing a skirt-like bottom. The dog has a belt around its waist and is gesturing with its right hand. The dog is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The dog now appears as a warrior with an axe. The dog is shirtless, muscular, has tattoos, and is smiling with a determined look on her face. The background is the same mountain range as before. The next scene shows the dog still as a warrior, and he is holding an axe with a golden axe head.

Model File and Inference Workflow

📥 Download Links:

warrior_45_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: warr10r warrior it

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 a warrior!
Epochs: 45

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!