holotard / README.md
hollowstrawberry's picture
Update README.md
e676910
|
raw
history blame
7.17 kB
metadata
license: creativeml-openrail-m
language:
  - en
pretty_name: Hololive vtuber LoRAs and TIs
task_categories:
  - question-answering
tags:
  - stable-diffusion
  - vtuber
  - hololive
  - stable diffusion 1.5
  - textual-inversion
  - lora
  - character
  - text-to-image
pipeline_tag: text-to-image
metrics:
  - character

Models

These were mixed with a model trained on tens of thousands of vtuber images. The 3.1 version knows more non-hololive youtubers, but may have lower quality.

Click here for a comparison

 

Loras (and TIs)

All known holo Loras will be linked to and backed up here. Put them in your stable-diffusion-webui/models/Lora folder. Use them in your prompt like this: <lora:filename:1>

Most Loras work best with a weight of 0.7 as the default of 1 might fry your image.  

All Vtubers

You can use it with any model, but may have lower quality than Loras for individual vtubers or a full merged model.

Small Loras

These were resized to a quarter of their original size. Give them a higher weight than their full counterparts to preserve detail. Find them in this repo.

Click here for a comparison
 

Outfits

Main purpose of this repo.

HoloEN

HoloID

  • Ayunda Risu
  • Moona Hoshinova
  • Airani Iofifteen
  • Kureiji Ollie (Default, Olivia)
  • Anya Melfissa
  • Pavolia Reine
  • Vestia Zeta
  • Kaela Kovalskia
  • Kobo Kanaeru (Default)

HoloJP