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. If you don't know what it is or how to use it effectively, here's an extensive guide about it.
Recommended additional resources:
- orangemix.vae.pt - without a VAE selected in the settings your colors will look faded.
- TagComplete to view all available anime tags as you write your prompt.
- Image Browser (updated fork) to view your past images and their prompt metadata.
- Lycoris extension to be able to use locons and lohas, which are new types of lora.
- EasyNegative - put it in your
stable-diffusion-webui/embeddings
folder and writeEasyNegative
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 here.
- HeavenOrangeHolos
- HeavenOrangeVtubers4-p1
- AOM3_hll4-p1
- Grapefruit4.1_hll4-p1
- Manually mixing hll1/hll3.1/hll4-p1 with your desired model
Loras
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
, but some recent ones work well at the default of 1
.
Locons and Lohas are new types of Lora, they work the exact same but you need this extension to use them.
Learn to make your own Loras with my guide.
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 from 144 MB to 18 MB or 36 MB 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 works because dim 128 used to be the default setting for making Loras but that was completely overkill and dim 8/16/32 work just as well.
This was done by me. Find them here.
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 or in the text files next to each Lora.
HoloEN
- Mori Calliope (Default) (2)
- Takanashi Kiara (Default) (Elegant)
- Ninomae Ina'nis (4 Outfits)
- Gawr Gura (Default) (2) (Atlantis)
- Amelia Watson (3 Outfits) (Default, Casual, Hime)
- Irys (Default)
- Ceres Fauna (Default, Casual) (2) (Default + Cow Bikini)
- Ouro Kronii (Default, Milf) (2) (3) (4)
- Nanashi Mumei (Default) (Friend)
- Hakos Baelz (Default) (Generic)
- Tsukumo Sana (Default)
HoloID
- Ayunda Risu (Default + Witch)
- Moona Hoshinova (Default)
- Airani Iofifteen (Default)
- Kureiji Ollie (Default, Olivia)
- Anya Melfissa (Default)
- Pavolia Reine (Casual)
- Vestia Zeta ({locon} Default)
- Kaela Kovalskia (Default)
- Kobo Kanaeru (Default) (2)
HoloJP
- Tokino Sora (Default)
- Roboco-san (Default) ({locon} 2)
- Sakura Miko (Default)
- Hoshimachi Suisei (Default) (Generic)
- Azki (Idol + Casual) (Diva1, Diva2)
- Yozora Mel (3 Outfits)
- Shirakami Fubuki (8 Outfits) (Default, Formal, Oba-chan, Techwear) (Generic) (Kurokami)
- Natsuiro Matsuri (5 Outfits) (Default, Bikini)
- Akai Haato / Haachama (Default)
- Aki Rosenthal / Akirose (Default)
- Minato Aqua (Default) (2) (Neko)
- Murasaki Shion (Default)
- Nakiri Ayame (Generic)
- Yuzuki Choco (Default)
- Oozora Subaru (5 Outfits)
- Ookami Mio (5 Outfits)
- Nekomata Okayu (Default) (2)
- Inugami Korone (Default)
- Usada Pekora (9 Outfits) (Default) (2) (Seifuku, Bunnysuit)
- Shiranui Flare (Default + Third)
- Shirogane Noel (5 Outfits)
- Houshou Marine (Default)
- Uruha Rushia (9 Outfits)
- Amane Kanata (Default) ({locon} Third)
- Tsunomaki Watame (4 Outfits) (Towa+Watame)
- Tokoyami Towa (Default + Suspenders) (2) (Towa + Watame)
- Himemori Luna (Default, Astral Dress)
- Kiryu Coco ({loha} 5 Outfits)
- Yukihana Lamy (4 Outfits)
- Momosuzu Nene (Casual)
- Shishiro Botan (Default)
- Omaru Polka (Clown, Gyaru)
- La+ Darknesss (Default) (2)
- Takane Lui (Default)
- Hakui Koyori (3 Outfits) (2)
- Sakamata Chloe (Default) (Spring)
- Kazama Iroha (Default) (2)
Staff
- A-chan (Default)
(Legacy) Embeddings
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.
Nobody makes these anymore because Loras are easier to make and work better for most applications.
- Ninomae Ina'nis ({TI} Default) ({TI} Generic)
- Hoshimachi Suisei ({TI} Default) ({TI} Alternate)
- Inugami Korone ({TI} Default)
- Nekomata Okayu ({TI} Casual)
- Oozora Subaru ({TI} Generic)
- Uruha Rushia ({TI} Default, School, Black, Pink)
- Shishiro Botan ({TI} Default)
- La+ Darknesss ({TI} Default)
- Sakamata Chloe ({TI} Default 1&2)