santa hat
deerdeer nosedeer glow
Sign In

March 7th | Honkai Star Rail

1.6k
12.1k
93
Type
LoRA
Stats
10,843
Reviews
Published
Feb 18, 2023
Base Model
SD 1.5
Training
Steps: 2,667
Epochs: 20
Trigger Words
march7th
multicolored_eyes
pink hair
ribbon earrings
Hash
AutoV2
7641120D81
default creator card background decoration
Zipsy's Avatar
Zipsy

UPDATE

less overfitted model trained with more images generated by this LoRA, more detail looks at preview images & changes logs.
TL:DW/R

  • march7th_HSR for more detail original clothes

  • march7th_HSR_face for flexibility

Hello...

This is a LoRA for March 7th character from Honkai Star Rail, trained in Anythingv4.5 for 20 epochs with 40 images 10 repeats,

its match the character pretty well with model like anything or , for more information you can see the image previews.

for the weight i recommended using around 0.6-0.8.

some time her clothes can be some problem if you want to mix it with other prompt, i suggest to use (jacket, white shirt, choker:2) tinker with the weight. there some example of it.

as for the trigger words, i think you can use

march7th, short hair, multicolored_eyes, pink hair, bangs, blue_eyes, long locks, ribbon earrings, shirt, skirt, choker, jacket

i guess that is all, thanks you....

Edit:
So i forgot some images that i use for the preview using control net when looking for pose or propotions, Here some guide to use ControlNet

  • Go towards extensions tabs and install this extension, https://github.com/Mikubill/sd-webui-controlnet

  • Download ControlNet model (https://huggingface.co/lllyasviel/ControlNet/tree/main/models) (recomended the openpose one) and place it inside sd-webui-controlnet/models extension folder

  • After installing, a tab named Control Net should be appeared in txt2img or img2img

  • Open the tab and use this image as a guidelines, pretty much use openpose preprocessor and openpose model then place the image that you want to use inside the tab.

  • Sometimes this method not working, you can use openpose stickman instead, here my collection of openpose stickman (set preprocessor to none like this)

  • Then just generate images like usual, just leave the ControlNet enabled. the image should resemble the pose

ps im just gonna leave some of this here :>

pixiv

twitter

facebook