holotard / README.md
hollowstrawberry's picture
Update README.md
0745530
|
raw
history blame
10.2 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

Preamble

These resources are intended to be used with stable-diffusion-webui.

Recommended additional resources:

  • orangemix.vae.pt - without a VAE selected in the settings your colors will look faded.
  • TagComplete to view all available image tags as you write your prompt.
  • Image Browser (bugfix fork) to view your past images and their prompt metadata.
  • EasyNegative - put it in your stable-diffusion-webui/embeddings folder and write EasyNegative in your negative prompt to drastically improve your images.

 

Models

These were mixed with hll, a model trained on tens of thousands of vtuber images. The 3.1 version knows more non-hololive vtubers, but has a different style. Many more mixes can be found in the same repo these come from.

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

TIs or textual inversion embeddings are an older but lighter alternative. They go into your stable-diffusion-webui/embeddings folder and are used like a normal word in your prompt.

 

All Vtubers

These can do a wide variety of vtubers with only 1 Lora, but may have lower quality than a single Lora for each character. For a compromise between size and quality, try the Small Loras below.

 

Small Loras

These were scaled down to 1/7 of their original filesize and perform almost the same. They need a higher weight than the original to preserve detail. If one performs poorly for you, try the original instead.

This was done by me. Find them here.

Click here for a comparison

 

Outfits

Main purpose of this repo. Format: (Source 1) (Source 2)... where each source can have multiple outfits.

The default outfit is the first/main one for that talent. Generic means it's not trained on a particular outfit and can do various clothing. In any case, most Loras can change clothes.

Example usage of each outfit can be found in the metadata of the image previews next to each Lora.

HoloEN

HoloID

HoloJP