1MB LORAテスト
1MB LORA test
*********************************************
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 (7)
My impressions after creating 1MB LORA were that it could be used as long as the actions and costumes were limited.
Even so, a lot of details are omitted, so to maintain a certain level of quality, I needed 8MB, and if I wanted to add action and costumes, I needed 16MB.
32MB may be better when adding detailed shading or creating something more complex.
If you're trying to include multiple characters in one LORA, I think it's more stable to use double the capacity, like 16 for 2 characters that don't take action, and 32 for 2 characters that take action.
----------------原文,Original text-------------------
1MB LORAを作成した感想ですが、アクションや衣装を限定すれば使えなくはない、と言った感じでした。
それでも、細部がかなり省略されるので、一定のクオリティを保つ為には、8MB、アクションや衣装を追加するなら16MB、みたいな感じでした。
詳細な陰影を付けたり、より複雑な物を作る時は32MBが良いかもしれません。
一つのLORAに複数のキャラクターを入れようとする場合、倍の容量を使用した方が安定する気がします、アクションしない2キャラクターなら16、アクションする2キャラクターなら32みたいな。
was it not hard to make because only 1 episode is out and there are not enough training images?
I think that modern anime is quite easy to learn because the image quality is stable due to CG animation.
最近のアニメは、CG作画で画質が安定しているので、かなり学習させやすいと思います。
Hey can you make "Mikasa" From AoT ? please
"Mikasa Ackerman" has many high quality LORAs created by others.
Do you really want what I made?
If you really want it, please add a "★" and comment again on the evaluation page.
Once that's done, I'll think about whether to make it or not.
"Mikasa Ackerman"は、他の方が作成した高品質なLORAが沢山ある。
本当に私が作った物が欲しいのですか?
本当に欲しいのなら、評価ページで"★"を付けてもう一度コメントを下さい。
それが行われたら、作るかどうか考えます。
Hello, your models are incredible, I have been testing them and they maintain the aesthetics of the anime. If you don't mind, could you make a model of Kokkoro? but from the anime version of the series Princess connect: Re dive
I can't create it because I don't have the material image.
素材画像を持っていないので作れません。
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.