Подробности
Рекомендовано
Hsena_v1
JAV hikari_sena

JAV hikari_sena

2.2K
51
10
#Сексуальный
#Женщина
#jav
#gravure
#Где мужчина
#актриса
#знаменитость
#японский
#?????звезда
#Реализм

Imitation model. Modelled after Japanese AV star Hikari Sena (瀬名ひかり [2020]; previously known as Sayuri Mitsumoto 光本小百合).

This week we got 2 slightly athletic ones.

Dont let her baby-face deceive you, on whats underneath that innocent look. Her look is considered average, but its the comfortable kind of average. She puts off a somewhat "amateur" vibe; but her performance is nowhere amateur. Body physique wise, this LoRA will go well with most clothing styles (got lucky that quite a substantial bit of her training data were full body shots - for you stat-hungry JAV fanboys: she's: 93 (G Cup)-61-93cm).


Recommended LoRA strength: 1.0 (0.8-1.2 are plausible range dependent on checkpoints; higher values lead to younger facial features and in some checkpoints, big 0ppai)

Main Prompt:

hikarisena_jav, breasts,

variations: single hair buns, black hair, tied hair

facial variations: natural makeup, grin, teeth, parted lips*

*I do not find the need to use the facial prompts, as most checkpoints recreate her lazy eyes and parted lips perfectly

Checkpoints that work well for this LoRA:

1) Realisian, or any of the Magicmix variants. Should rename it JAV-sian at this point..

2) RealisticMix. Stable, good success; ??????? alittle off, but everything else is fine.

3) ClearRealismMix-Eur, or asian-based/eurasian checkpoints. works 75% of the time with less prompts (i.e. more flexibility).

4) PerfectWorld, or other photoRealistic ?????? models (European model works fine for this LoRA). Tend to over-correct her facial features to be "perfect world ish", but overall still OK.

Note for achieving good resemblance:

Use Adetailer for baseline generation (at 512, 768 etc) only, try to control LoRA strength at 0.9-1.0, adjust your denoise accordingly. For this LoRA, recommended to use Adetailer at ~0.4 denoise strength for close-up, and 0.45 to 0.55 for full body.

For this LoRA, you dont need to set the prompts for Adetailer separately. I prefer to use just the main prompt, and turn ADetailer on, since you dont want to overload the makeup, this actress generally do very light blush and touch-on only.

Recommended approach: is to not use HiRes, but upscale it with img2img instead.

Use a denoise strength of 0.25 (anything higher will overcorrect face during the process), and turn off Adetailer.

Issues:

So far no issues, apart from badHands, and extensive use of inpainting x10 to make the LoRA wear her clothes properly to post this, big 0ppai problems.

Post-production edits/Reproducibility:

Some preview images underwent inpainting manually on the clothing part because of the nature of some of the training data. Prompt responsibly.

Tomorrow, big momma might be ready for release.. lets see.

Happy prompting. And do share [SFW] creations~

Просмотреть перевод

Оценки и отзывы

-- /5
0 оценок

Еще не получено достаточно оценок или комментариев

R
ryk_civit
168
2.8K
Объявление
2024-03-20
Публикация модели
2024-03-20
Обновить информацию о модели
Детали модели
Тип
LORA
Время публикации
2024-03-20
Базовая модель
SD 1.5
Слово-триггер
hikarisena_jav
breasts
Копировать
Версия введения.

v1. Initial release. All epoches perform similar. so the last epoch was picked. retaining last 3 epoch for testing.

trained on 86 images. at 512 reso.

Very good performance on most [asian] checkpoints. rework wont be necessary, I guess.

Область действия лицензии
Источник: civitai

1. Права на репостнутые модели принадлежат оригинальным создателям.

2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить

Диапазон лицензий на создание
Прямая трансляция
Смешение
Разрешить загрузку
Коммерческая лицензия
Сгенерированные изображения можно продавать или использовать в коммерческих целях
Разрешить перепродажу моделей или продажу после интеграции
QR Code
Скачать приложение SeaArt
Продолжайте путешествие по AI-творчеству на мобильном устройстве