SDXL LoRA/LyCORIS works best on its original training model. You may need to reduce weight when using it with other models or additional LoRAs.
LyCORIS Combination Recommendation: Try using four of my LyCORIS models with the following weights: 0.4, 0.3, 0.2, 0.2 (or any combination with a total weight around 1.0).
I will release multiple versions for a few popular models. Feel free to request for artist or model.
Version naming convention: MajorVersion.MinorVersion [BaseModel]
MajorVesion: For big updates that can apply to any style LoRA. For example, training parameter update.
MinorVersion: For small updates that only apply to this LoRA. For example, epoch selection, removing a certain image from dataset.
BaseModel: SDXL LoRA/LyCORIS works best on the model that it was trained on.
Description
FAQ
Comments (8)
Excellent job. I always appreciate it.
I would very much like to see a LORA by "soaryuna（侑了个侑）", the official azurlane painter. If there is not enough data, I am happy to blend with other azurlane painters. (kincora,yunsang,活断層 etc)
soaryuna(侑了个侑)
https://danbooru.donmai.us/posts?tags=soaryuna
azurlane illustrator
https://azurlane.wikiru.jp/index.php?CV%E3%83%BB%E3%82%A4%E3%83%A9%E3%82%B9%E3%83%88%E3%83%AC%E3%83%BC%E3%82%BF%E3%83%BC#u9b5585f
I want a picture, and I don't need the Azur Lane style, and I would be very happy if there were no rigging, etc.
Hi, thanks for your support. I can't get enough images from soaryuna. Seems like the artist doesn't have pixiv or twitter.
I'm looking for a dataset around 100 images. Consider I can only get less than 10 images from soaryuna, it is basically another artist's style LoRA.
What are your favorite artists other than soaryuna? Give me a few in order since I will also exclude images with rigging.
@silvermoong Thank you. You are God. Noted.
The names from the following sites, in order of priority, list the illustrators whose taste is similar to that of soaryuna-sensei and whose illustrations I prefer.
As for the outfits, you may include them if you have no choice (to the extent that you can exclude them with negatives).
If there is enough material, it is okay to discard anything below medium priority. Anything too juvenile can be excluded.
(Priority High)
soaryuna
kurumi普拉斯+
KIn（kincora）
雲桑（yunsang）、YD、全班最菜嘤嘤嘤(YYY_( ´･ᴗ･` )) 、活断層
トリダモノ （Please use only the images provided to Azur Lane.）
八重樫南 （Please use only the images provided to Azur Lane.）
DSマイル、MKiiiiii33、AIKO、ぴょん吉、ポップキュン、LAL!ROLE、木shiyo
絵師不明（ゴールデンハインドのイラストレーターhttps://azurlane.wikiru.jp/index.php?%E3%82%B4%E3%83%BC%E3%83%AB%E3%83%87%E3%83%B3%E3%83%BB%E3%83%8F%E3%82%A4%E3%83%B3%E3%83%89）
（Priority Medium）
Manjuuアートグループ、Bach Do(Dishwasher1910) 、Liduke、股间少女老妹鹅、Chuzenji、科学、Vilor
If there is anything we can do to help, we would love to!
Thank you very much.
@silvermoong PS, I am happy to learn in 7thAnimeXL and by extension animagine 3.1.
@mumumu1295 Not sure if this is what you are looking for: https://civitai.com/models/428950
I started with PonyV6 as Animagine V3 has an issue with transparent background. Not sure if it is fixed in V3.1. I will try it later.
@silvermoong Thanks! I haven't used pony but will give it a try! Looking forward to 3.1 as well.
Thanks for great works.
I think your demo images were made by i2i, because I could search original images easily.
Did you suceed in Michiking style images from t2i?
If so, could you provide some advice to create it.
Thanks for your support!
All demo images were generated by t2i. You can click into images to get the prompts.