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.
*********************************************
このLORAは、取り扱いが難しく、上級者向けです。
状況に応じて、各種ウェイト、トリガー、プロンプト、使用するモデル、などを様々に変化させる必要があります。
This LORA is difficult to use and is for advanced users.
Depending on the situation, you may need to vary the various weights, triggers, prompts, models used, etc.
*********************************************
使用したVAE VAE used
"vae-ft-mse-840000-ema-pruned.safetensors"
*********************************************
LORA推奨ウェイト：0.7、
DPM++ 2M SDE Heun Karras ステップ30
高解像度補助:R-ESRGAN 4x+ Anime6B,倍率2倍、ステップ15、デノイジングストレングス0.5
ADetailerを使用しface_yolov8nで顔修正を行っています。
LORA recommended weight: 0.7,
DPM++ 2M SDE Heun Karras Step 30
High resolution auxiliary: R-ESRGAN 4x+ Anime6B, 2x magnification, step 15,Denoising strength 0.5
I am using ADtailer to modify the face with face_yolov8n.
*********************************************
"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 (3)
hi, nice lora! can i have the training dataset of this lora? this will really help me a lot, thank you very much!
Hello, the LORA that I create uses a very special learning method, and I taught it to several people, but no one understood it and said, ``This dataset is useless, a proper LORA.'' cannot be made.”
That's what I've been told. See my LORA metadata.
If you are still interested, please contact us again.
@jibunsagasinotabi okay, i will take a look. btw i think the dataset should be useful to me. i remember u have given many 5 stars to me, so i think u must have known that im developing 100% automated training pipeline. so please believe, im interested in all kinds of novel solution on lora training. lol
this is my discord server, we can talk about the new training method more: https://discord.gg/XzGvuUKN
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.