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: >-
      B0x13ng Boxing video two boxers are in the ring, but one of them is
      significantly shorter than the other. The shorter female fighter in black
      shorts is aggressively throwing punches, trying to reach his taller
      opponent. The taller fighter, wearing black shorts, simply holds out his
      glove on the shorter fighter’s forehead, keeping her at a frustrating
      distance.
    output:
      url: example_videos/boxing1.mp4
  - text: >-
      B0x13ng Boxing Video The boxer throws a left jab and then a right hook,
      landing a knockout blow.
    output:
      url: example_videos/boxing2.mp4
  - text: >-
      B0x13ng Boxing Video The boxer throws a quick series of jabs and then a
      right cross.
    output:
      url: example_videos/boxing3.mp4

Boxing LoRA for Wan2.1 14B T2V

Overview

This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos of people boxing.

Features

Trained on the Wan2.1 14B T2V 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: B0x13ng Boxing video two boxers are in the ring, but one of them is significantly shorter than the other. The shorter female fighter in black shorts is aggressively throwing punches, trying to reach his taller opponent. The taller fighter, wearing black shorts, simply holds out his glove on the shorter fighter’s forehead, keeping her at a frustrating distance.

Prompt: B0x13ng Boxing Video The boxer throws a left jab and then a right hook, landing a knockout blow.

Prompt: B0x13ng Boxing Video The boxer throws a quick series of jabs and then a right cross.

Model File and Inference Workflow

📥 Download Links:

boxing_10_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: B0x13ng Boxing Video

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 T2V
Training Data: Trained on 1 minute of video comprised of 15 short clips (each clip captioned separately) of boxing footage.
Epochs: 10

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!