v1.2
トリガーはスペル違うけど気にせずコピペして。
Trigger is spelled differently, but don't worry, just copy and paste.
*********************************************
アニメLORAですが、アニメモデルとの相性は良くありません、"kantanmix"以外のモデルで出力する場合は2.5Dモデルで試してみて下さい。アニメモデルの場合は、重量を下げ、プロンプトで補正したりする事が必要です。
Although it is an anime LORA, it is not compatible with anime models. If you want to output with a model other than "kantanmix", please try using a 2.5D model. For animated models, it may be necessary to lower the weight and make corrections with prompts.
*********************************************
好きな衣装や、背景、ポーズを組み合わせて下さい。
Please combine your favorite costumes, backgrounds, and poses.
*********************************************
weight 0.7、ADetailerを使用しface_yolov8nで顔修正を行っています。
高解像度補助:R-ESRGAN 4x+ Anime6B,倍率2倍
Weight 0.7 ADetailer is used and face_yolov8n is used for face correction.
Hires.fix:R-ESRGAN 4x+ Anime6B,2x magnification
*********************************************
"Detail Slider - LoRA"
https://civarchive.com/models/153562?modelVersionId=171989
"Detail Tweaker LoRA (细节调整LoRA)"
https://civarchive.com/models/58390?modelVersionId=62833
"flatBG"
https://civarchive.com/models/81298/flatbg
"noline"
https://civarchive.com/models/81309/noline
"boldline"
https://civarchive.com/models/81313/boldline
"Zoom Slider - LoRA"
https://civarchive.com/models/114460?modelVersionId=123732
"ADetailer"
(インストールは自己責任でお願いします)(Please install at your own risk.)
顔の詳細を修正する追加機能
Additional features to correct facial details
https://github.com/Bing-su/adetailer
Embeddings
"Fast Negative Embedding (+ FastNegativeV2)"
https://civarchive.com/models/71961?modelVersionId=94057
"EasyNegative"
https://civarchive.com/models/7808/easynegative
"negative_hand Negative Embedding"
https://civarchive.com/models/56519/negativehand-negative-embedding
Description
テスト
FAQ
Comments (16)
Hurra'! We have also a Mendo updated!
How did you get more images to improve the LORA?
Did you downloaded the serial?
I watched it by chance, it's a limited edition.
偶然視聴しました、限定的な物です。
@jibunsagasinotabi Ok, I've tested the Lora. Will tell more about, later.
Meanwhile I will post the images, few of them each day, because the rule says "creator will receive 50 Buzz" each time a user post images.
So, If I post all images at same time, you receive only 50 Buzz. But if I post day by day, you should receive more and more....
@settima_ai
Although I haven't confirmed it, the terms and conditions say "for each user who posts an image on a model" (50,000 months), so I think the same user can only receive it once when they post on the same model.
I think you can get it if you submit it to another model.
確認した訳ではありませんが、"モデルに画像を投稿するユーザーごと"(50000ヵ月)、と規約がされているので、同じユーザーが同じモデルに投稿した時に貰えるのは1回だと思います。
別のモデルに投稿する場合は貰えると思いますが。
@settima_ai
There is no need to force yourself to post, just post if you want to use it in a test, share information, show off an image, etc.
My PC spends most of its time learning LORA, so I don't have time to generate images, so it would be helpful if you could test it out lol
無理に投稿する必要は有りません、テストで使用し情報を共有したい、画像を披露したい、等の場合に投稿して頂ければ十分です。
私のPCは、殆どの時間をLORA学習に充てているので、画像生成する時間が取れないので、テストして貰える分には助かりますがw
@jibunsagasinotabi Hello again! As test, one day is passed and I posted a new image here (Lum kissing Mendo) and I received 25 Buzz as my first image posted of today.
Can you please confirm you did not receive your 50 Buzz for this action?
@settima_ai
You can only get a buzz once, so I don't think you need to worry about it. Please post whenever you like.
バズを貰えるのは1回のみです、気にする必要は無いと思います。好きな時に投稿して下さい。
Review:
This Lora is very good!
High success rate, the idea of packing Lum and Ryoko inside the Mendo LORA is a great idea and makes Regional Prompting much more easy to work.
In the past, I tryied to add more character's LORA but getting only bad graphic. It's a great fun now to add 2 or 3 of them in the same image and I will post some examples during next days.
The biggest limit of this LORA is the "checkpoint compatibily", in other words it works well only with few of them: CalicoMix, SardonyxRedux, STYM2D-Anime (if you still have it). From the demo gallery is clear that it works best with kantanmix, I suspect because it's the checkpoint used to train it, but I still have to install and test it.
So, if you use one of those checkpoint you'll get great results. With other checkpoints, you'll get strange looking faces, or faces without eyes and so on. Some checkpoints may work well sometimes, but in general, success rate will be low.
@settima_ai
Thank you for your valuable feedback.
It has been confirmed that the LORA I create does not work well if quality prompts are included in the positive prompts.
Try removing high-quality prompts from the positive prompts (including Masterpiece) and adding low-quality prompts to the negative prompts.
We have confirmed that EasyNegative is effective.
貴重なご意見有難うございます。
私が作るLORAは、ポジティブプロンプトに、品質系のプロンプトが含まれると、上手く作動しない事が確認されています。
ポジティブプロンプトから、品質系のプロンプトを排除(マスターピース含む)し、ネガティブプロンプトに低品質系のプロンプトを追加してみて下さい。
EasyNegativeが効果的なのは確認しています。
@jibunsagasinotabi Interesting! Thank for this information!
@settima_ai
Unfortunately, I have only been able to test this on a limited number of models.
Not sure if this works for many models.
残念ですが、私は限られたモデルでしか、これをテスト出来ていません。
多くのモデルでこれが有効かは不明です。
Hello jibunsagasinotabi,
Next one I will like to post some images made for fun, there is no nudity but the images are spicy, like fishnet highthigs, garter belt, lingerie and so on...
Is ok for you?
As long as it's not a direct "NSFW" image, it's okay.
直接的な"NSFW"画像で無ければ大丈夫です。
@jibunsagasinotabi Ok, lets try!
This new theme is called "Mendou is starting a new business in town, at night!
Let me know if it makes you laugh.
Or, if you dont like, I will remove.
@settima_ai
I think there is no problem.
問題無いと思います。
Hello. If you still have the datataset, a Illustrious version would be great!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.





