metadata

license: apache-2.0
language:
  - en
base_model:
  - Wan-AI/Wan2.1-T2V-14B
pipeline_tag: text-to-video
tags:
  - text-to-video
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: >-
      The [d00m doom first person gameplay] showcases a player using a rocket
      launcher in a room with a cyberdemon, the text "TARGET ACQUIRED" flashing.
    output:
      url: example_videos/doom1.mp4
  - text: >-
      The video shows [d00m doom first person gameplay] in a room with red walls
      and a lava pit. The player shoots a large monster with a rocket launcher.
    output:
      url: example_videos/doom2.mp4
  - text: >-
      [d00m doom first person gameplay] in a hellish arena, the player is
      picking up a super shotgun.
    output:
      url: example_videos/doom3.mp4
  - text: >-
      The [d00m doom first person gameplay] displays the player in a gray
      hallway with a chainsaw, the text "CHAINSAW ACQUIRED!" appearing on
      screen.
    output:
      url: example_videos/doom4.mp4

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

Overview

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!

Prompt: The [d00m doom first person gameplay] showcases a player using a rocket launcher in a room with a cyberdemon, the text "TARGET ACQUIRED" flashing.

Prompt: The video shows [d00m doom first person gameplay] in a room with red walls and a lava pit. The player shoots a large monster with a rocket launcher.

Prompt: [d00m doom first person gameplay] in a hellish arena, the player is picking up a super shotgun.

Prompt: The [d00m doom first person gameplay] displays the player in a gray hallway with a chainsaw, the text "CHAINSAW ACQUIRED!" appearing on screen.

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: [d00m doom first person gameplay]

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.

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 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

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!