Lora натрененные на синтетическом датасете и\или миксе нескольких художников.
В целях сокращения промпта и управляемости стиля.
______________________________________________________________________________________________________
Lora trained on a synthetic dataset and/or a mix of several artists.
In order to reduce the prompt and controllability of the style.
Description
Применение:
Триггеры = пони-скоры: score_9, score_8_up, score_7_up, score_6_up
Данные обучения:
Датасет состоит из артов anko1127, akziqi и minahamu(от сюда и название лоры) + арты с reference_only.
Я хотел передать эффект легких мазков краски и форму лица, вроде получилось :)
_____________________________________________________________________________________________________________
Application:
Triggers = pony-scores: score_9, score_8_up, score_7_up, score_6_up
Training data:
The dataset consists of art by anko1127, akziqi and minahamu (from here the name of the Lora) + art with reference_only.
I wanted to convey the effect of light strokes of paint and the shape of the face, it seems to have worked :)
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.