Amanatsu (Illustrious) - V1.1
하이라이트된 이미지
추천 프롬프트
1girl, masterpiece
추천 네거티브 프롬프트
signature
worst quality, bad quality
추천 매개변수
samplers
steps
cfg
resolution
vae
추천 고해상도 매개변수
upscaler
upscale
denoising strength
팁
Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures.
Use negative prompt 'signature' to avoid unwanted signatures in generated images.
Excluded metadata and franchise tags to improve output quality.
버전 하이라이트
Update to Style B that is now amanatsu
Improvements:
- A bit more stable with backgrounds, less random strange extra stuff appears
- Less blurry
- Better eyes (if they don't artifact or used with hires or adetailer)
- Slightly less artifacs (still many, hires or adetailer are recommended)
- Brighter in most occasions, without loosing the ability for darker images
Its based on hassaku 2.1, but have back mergin with style V1. So its a bit of a combo of V1 and hassakuV2.1. The versatility of 2.1 + the style of B in one model.
크리에이터 스폰서
Amanatsu aims to be a model with a distinctive detailed anime look.
My Discord for everything related to anime models and art. You can support me on my patreon.
_____________________________________________________
Supporters:
Thanks to my supporters Riyu, SETI and Kodokuna on my patreon!
_____________________________________________________
Using the model:
Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures as possible. If such features appearing in a image, please use prompt "signature" as negative.
Excluded metadata and franchise tags, don't use them. meta data -> something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".
Here are some good resolution options for SDXL:
1024 x 1024
1152 x 896
896 x 1152
1216 x 832
832 x 1216 (most recommended)
1344 x 768
768 x 1344
1536 x 640
640 x 1536
