Higurashi no Naku Koro ni Kira Style: https://civarchive.com/models/154232
When using the Civitai Generator, if you do not enable Enhanced Compatibility, abnormal results will be generated!
Setting the weights to approximately 1.0 is recommended.
If the generated image looks strange, set the CFG Scale to between 5 and 7.
Please Use NoobAI V-Pred 1.0 Checkpoint!
Activation tag : higurashimei
Recommend Prompt
Positive: higurashimei, (tag), (masterpiece, best quality, absurdres, highres), (newest, very awa), Negative: worst quality, worst aesthetic, bad quality, artistic error, old, ealry, mammal, anthro, furry, feral, semi-anthro, lowres, (bad), off-topic, multiple views, comic, very displeasing, displeasing, chromatic aberration, (extra digits), fewer digits, fewer, text, error, missing, jpeg artifacts, artist name, signature, twitter username, username, watermark, scan, unfinished, [abstract], variations, (((bad hands))), ai-generated, Characters supported by LoRA:
Furude Rika
Hanyuu
Houjou Satoko
Ryuuguu Rena
Houtani Nao
Maebara Keiichi
Sonozaki Mion
Sonozaki Shion
Akasaka Mamoru
(It comes out a bit weird)Akasaka Miyuki
Kimiyoshi Kazuho
Tamurahime No Mikoto
Tomitake Jirou(It comes out a bit weird)
Takano Miyo
The other characters may be able to be output.
Description
This LoRA has been converted from the existing DoRA to LoKR, and with mixed fp32 and bf16 training on two 4090s, it can now reproduce the art style in even higher quality.
FAQ
Comments (8)
MAKE NOOBAI NUMBER ONEEEEEEEE 1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣1️⃣🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴👑👑👑🤴👑🤴🤴👑🤴👑🤴👑🤴👑🤴👑🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴👑👑👑🤴👑🤴🤴👑🤴👑🤴👑🤴👑🤴👑🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴🤴👑👑👑🤴👑🤴🤴👑🤴👑🤴👑🤴👑🤴👑🤴
Just want to say that I'm always grateful to you for sharing updates of this great style, Munsy. It's always good to see updates from you. Have a great day! Thank you!
Merry christmas, Munsy!
Also I'm here to wish you a great new year too!
Thank you very much for all the great loras you shared over these years.
Only great days and good things for you, Munsy!
Thank you very much!
Munsy, happy new year!!!
Here to wish you an awesome year full of great things!
Thank you very much for everything, Munsy!
Happy new year!
Hi, your lora is probably the best i have seen. Which program did you use for training?
Do you know kohya_ss?
@munsy0227 Yes, did you stick to a specific template for the parameters? I can retrieve the training parameters from the safetensor via the lorainfo.tools page, but that's a bit clunky. I'll try my luck and see if I can adopt the parameters—I've built up a huge dataset for a character myself and tediously tagged and corrected everything by hand.
@sd1337806 Then, if possible, using an RTX 5090 or RTX 4090 to train with bf16 mixed precision should generally yield good results.