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
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.