着替えさせる事は困難です。
キャラクターの再現性は、使用するモデルによって、ウェイトやプロンプトを調整する必要が有ります。
It is difficult to change clothes.
For character reproducibility, it is necessary to adjust weights and prompts depending on the model used.
*********************************************
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)
do i have to use Adetailer to get the same face? the face isn't as perfect as yours.
(i copied your generation data and used the same settings and model), yet i can't get a perfect face :(
Personally, I think "Adetailer" and "Hires.fix" are essential.
Some advanced users produce good output without using this, but it was impossible for me, so I use the simplest "Adetailer" and "Hires.fix".
Please use at your own risk.
個人的には"Adetailer"と"Hires.fix"は、必須だと思っています。
一部の上級者の方は、これを使用せずに良好な出力をされますが、私には無理だったので一番簡単な"Adetailer"と"Hires.fix"を使用しています。
使用する際は、自己責任でお願いします。
@jibunsagasinotabi could you guide me on the steps of how you do it? do you use img2img or text2img when you use the adetailer?
@necroryona
Have you installed "Adetailer"?
"Adetailer"のインストールはしていますか？
Did you get the same output?
同じ出力は得られましたか？
@jibunsagasinotabi yes, i had it installed.
i enabled controlnet first to get the post i wanted.
then i enabled adetailer with it, and i got good face results, but the body wasn't very good.
thank you so much, i learned something new today thanks to you <3
Does that mean the body is different from the sample image?
体はサンプル画像と違うと言う事？
@jibunsagasinotabi it's the same, but if i add other LORAs it changes a bit.
@jibunsagasinotabi your LORA is perfect, my other loras are influincing it.
@necroryona
I got it.
In order to create a strong anime style, I had to learn more deeply, so it may not be compatible with other LORAs.
The models that can be used are limited in some places, and there are various problems.
We're working hard to maintain a strong anime style while remaining flexible and working well with other elements, but so far we haven't been very successful.
了解です。
強力なアニメスタイルにする為に、より深く学習させたので他のLORAとは相性があまり良く無いのかもしれません。
使用出来るモデルも限定的な所もあり、様々な問題を抱えています。
強力なアニメスタイルを維持しつつ、柔軟性を確保し、他の要素と上手く連携する事を目指して日々努力していますが、今の所あまり上手く行っていません。
@jibunsagasinotabi i think your LORAs are the most successful on this site !
@necroryona
There are many other wonderful LORAs and people who are creating models.
If there is someone who has created something good, please give them a "★" as well.
If the people who make good things are motivated, they will make even better things.
I look forward to the development of AI image generation.
他にも素晴らしいLORAや、モデルを作成されている方は沢山いらっしゃいます。
もし、良い物を作成している人がいたら、その人にも"★"を入れてあげて下さい。
良い物を作っている人がやる気を出したら、もっと良い物を作ってくれるはずです。
私はAI画像生成の発展を期待しています。
شكرا لك على صنع الصور كيلوا ✨! هل يمكنكم عمل صور لـ Creed diskenth من أنمي Black Cat؟ من فضلكم 💗
We are currently not accepting requests without images.
@jibunsagasinotabi Okay❤, but what do you mean by requests without pictures✨?
@afdlljyl453
This means that if the requester provides materials, there is a possibility that the request will be accepted.
If you simply want ~, there is no possibility of creating it.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.