Doom-FPS Open-Source Model - Free Generation of Classic Doom-Style Game Videos

Doom FPS

Developed by Remade-AI

LoRA trained on the Wan2.1 14B text-to-video model for generating classic Doom-style game videos

Text-to-Video EnglishOpen Source License:Apache-2.0 #Doom game style #First-person shooter video generation #90s retro gaming

Downloads 39

Release Time : 3/20/2025

Model Overview

This is a LoRA model specifically designed for generating first-person shooter game videos in the 90s Doom style. Based on the Wan2.1 14B text-to-video foundation model, it maintains style consistency and produces high-quality game footage.

Model Features

Style Consistency

Maintains consistency of 90s Doom game style across different objects and scene types

Simple Prompts

Provides easy-to-adjust simple prompt examples for quick user onboarding

Community Support

Offers Discord community support where users can freely use this LoRA to generate videos

Model Capabilities

Text-to-video generation

Game-style video generation

First-person perspective video generation

Retro game style rendering

Use Cases

Game Development

Game Concept Validation

Quickly generate game concept videos for visual validation in early development stages

Produces game footage with 90s Doom style

Game Trailer Production

Create retro-style trailer materials for indie games

Generates first-person perspective game combat scenes

Creative Content

Retro Game Style Video Creation

Provide video creators with retro game-style video content

Generates video clips with classic FPS game aesthetics

🚀 90s Doom FPS Style LoRA for Wan2.1 14B T2V

This LoRA, trained on the Wan2.1 14B T2V model, enables you to generate videos in the style of Doom!

🚀 Quick Start

This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos in the style of Doom!

✨ Features

Trained on the Wan2.1 14B T2V base model
Consistent results across different object and scene types
Simple prompt examples that are 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:

doom_8_epochs.safetensors - LoRA Model File
wan_txt2vid_lora_workflow.json - Wan T2V 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: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">[d00m doom first person gameplay]</code>

📄 Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work 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

📋 General Info

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

📈 Training Details

Property	Details
Base Model	Wan2.1 14B T2V
Training Data	Trained on 2.5 minutes of video comprised of 35 short clips (each clip captioned separately) of various Doom gameplay recordings.
Epochs	8

ℹ️ 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!

📄 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