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
キャラ固定テスト
FAQ
Comments (17)
パリピ孔明、見る前はネタ枠だと思ってたのに
見てみたらちゃんとストーリーがしっかりしてて面白かったなあ
意外と面白かったですねｗ
Please do chizuru mizuhara anime style lora
Unfortunately, I can't make it because I don't have the "material picture".
残念ながら"素材絵"を持っていないので作れません。
@jibunsagasinotabi I can collect it for you!
@forgerloid A total of about 30 images are required, including face close-ups, upper body shots, cowboy shots, full body shots, etc. It's okay if other people are included.
顔アップ、上半身、カウボーイショット、フルボディ、等の画像がトータル30枚程度必要です、他の人物が映っていても大丈夫です。
@forgerloid If the drawing is not unified, the character will be deformed according to the proportion of the data set. (If it is a dataset of anime + fan art, etc., the character will be somewhere in between.)
作画が統一されていない場合、データセットの割合でキャラクターは変形します。（アニメ+ファンアート等のデータセットなら、その中間ぐらいのキャラクターになります）
@jibunsagasinotabi here you go:
https://gofile.io/d/qf8rem
@jibunsagasinotabi Please anime(animefull-final-pruned-fp16.safetensors) for training the lora
@forgerloid I tried to do what I could with the teacher images I received, but I don't think I could have created anything better than LORA, which has been uploaded by others.
If the teacher image has whitewashing, defective hands, roughness, etc., it will be learned as is, so I deleted or cleaned several images and replaced them with other images.
頂いた教師画像で出来る事はしたつもりですが、他の方がアップされているLORAより優れた物が出来たとは思いません。
教師画像に白塗り、不具合のある手、粗などがある場合、そのまま学習してしまう為、画像を数点削除したりクリーニングし、代わりに他の画像を入れました。
https://civitai.com/models/159686/chizuru-mizuhara-rent-a-girlfriend-lora
@forgerloid Have you tried it?
試してみましたか？
@jibunsagasinotabi Thank you very much for doing it. I have tried it, it works well for me!
@forgerloid That's good
それは良かった
Hello. Where can I get the DP++ 2M SDE Heun Karras?
I was able to get it automatically after updating "StableDiffusion" to the latest version.
"StableDiffusion"を最新版にアップデートしたら自動的に入手出来ました。
What's the version?
@san0820 v1.6
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.