### angry-face open source model - Free to help quickly convert and generate angry face videos

Angry Face

Developed by Remade-AI

LoRA trained on the Wan2.1 14B I2V 480p model for generating angry expression video conversions

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

Downloads 204

Release Time : 4/1/2025

Model Overview

This LoRA model specializes in converting neutral expressions to angry expressions in video generation, suitable for image-to-video tasks.

Model Features

Cross-Object Type Consistency

Maintains consistent angry expression conversion effects across different object types

Concise Prompt Structure

Provides an easily adjustable concise prompt template structure

Efficient Training

Achieves good results with only 50 seconds of training video data

Model Capabilities

Neutral to Angry Expression Conversion

Image-to-Video Conversion

Facial Expression Dynamic Generation

Use Cases

Expression Generation

Angry Expression Conversion

Convert neutral expression videos to angry expression videos

Generates videos with angry expressions and corresponding actions

🚀 Angry Face LoRA for Wan2.1 14B I2V 480p

This LoRA is trained on the Wan2.1 14B I2V 480p model, enabling you to generate angry - faced videos.

🚀 Quick Start

This Angry Face LoRA is based on the Wan2.1 14B I2V 480p model. You can download the necessary files and follow the recommended settings to start generating videos.

✨ 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:

angry_face_5_epochs.safetensors - LoRA Model File
wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI

📚 Documentation

Recommended Settings

Property	Details
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;">4ngr23 angry face</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.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

Property	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!

🌐 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!

📄 License

This project is licensed under the Apache - 2.0 license.

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