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 man begins with a neutral expression. His expression changes to 4ngr23
      angry face, and he starts yelling. He then throws his arms up while making
      the 4ngr23 angry face.
    output:
      url: example_videos/1.mp4
  - text: >-
      The video starts with a man looking at the camera with a neutral face.
      Then his facial expression changes to 4ngr23 angry face, and he begins to
      yell with clenched fists. 
    output:
      url: example_videos/2.mp4
  - text: >-
      The video starts with a man looking forward with a neutral expression.
      Then his facial expression turns to 4ngr23 angry face, clenching his
      fists. The man then begins yelling and making the 4ngr23 angry face.
    output:
      url: example_videos/3.mp4

Angry Face 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 yourself or your friends angry!

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

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 man begins with a neutral expression. His expression changes to 4ngr23 angry face, and he starts yelling. He then throws his arms up while making the 4ngr23 angry face.

Prompt: The video starts with a man looking at the camera with a neutral face. Then his facial expression changes to 4ngr23 angry face, and he begins to yell with clenched fists.

Prompt: The video starts with a man looking forward with a neutral expression. Then his facial expression turns to 4ngr23 angry face, clenching his fists. The man then begins yelling and making the 4ngr23 angry face.

Model File and Inference Workflow

📥 Download Links:

angry_face_5_epochs.safetensors - LoRA Model File
wan_img2vid_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: 4ngr23 angry face

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.

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 50 seconds of video comprised of 11 short clips (each clip captioned separately) of people being angry.
Epochs: 5

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!