******Quality Prompt******
masterpiece,best quality,good quality,newest,
******Negative prompts******
lowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark,
*********************************************
使用したVAE VAE used
“sdxl-vae-fp16-fix”
" sdxl_vae"
https://huggingface.co/stabilityai/sdxl-vae/tree/main
*********************************************
LORA推奨ウェイト：0.8～1.0
Euler a か DPM++ 2M ステップ20～30
CFGスケール 5.5～7
高解像度補助:R-ESRGAN 4x+ Anime6B,倍率1.5倍、ステップ5～15、デノイジングストレングス0.5～0.6
ADetailerを使用しface_yolov8nで顔修正を行っています。
LORA recommended weight: 0.8～1.0,
Euler a or DPM++ 2M Step 20～30
CFG Scale 5.5～7
High resolution auxiliary: R-ESRGAN 4x+ Anime6B, 1.5x magnification, step 5～15,Denoising strength 0.5～0.6
I am using ADtailer to modify the face with face_yolov8n.
Description
テスト
FAQ
Comments (4)
This is great and classic. You can try more similar themed clothes. Then, there are still not completed in "can can bunny Premiere 2", such as Hiyama Yuki (檜山有紀) and Higashiyama Hinao (東山日奈緒)...Not sure if it's in your plan?
It’s just that their physiques and heights are too close to real girls...but its background and music are great!
@ghostpaint
Thank you. This LORA was created at the request of a client who provided detailed images of the costume, so I have no plans to create anything else.
@jibunsagasinotabi If you don't have a plan, maybe I will try to train lora, because they are from the same game company.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.