A red-haired sorceress wearing a large black witch hat, black corset with white lacing, and a flowing purple skirt with a slit stands outdoors at night holding a twisted wooden staff.
A blonde fairy with wings, pointy ears, and a green dress is floating at night surrounded by glowing light particles and blue butterflies.
Portrait of Miyuki Inaba with short brown hair, brown eyes, and a grey tank top, hand resting on forehead against a white background.

推奨プロンプト

1girl,1boy,2girls,characters,copyright,style,general tags,rating,score_9,score_8_up,score_7_up

score_9, 1girl, solo, white hairband, white background

推奨ネガティブプロンプト

score_4,score_5,score_6,source_pony,source_furry,monochrome,realistic,rough sketch,fewer digits,extra digits,3d,photo,hyperrealistic,signature,artist name

score_4, score_5, score_6, source_pony, source_furry, monochrome, 3d, photo, hyperrealistic, realstic, rough sketch, fewer digits, extra digits, signature, artist name

推奨パラメータ

samplers

Euler a

steps

25

cfg

6

clip skip

2

resolution

832x1216

vae

sdxl_vae_fix.safetensors (551eac7037)

ヒント

Use score tags at the end when using artist tags.

Score tags help generate average anime illustrations without excessively tuned styles.

To increase detail or change styles, use 'NovelAI' style prompting or 'lora' models.

クリエイタースポンサー

v2.0

Trained by 60k images from Danbooru and Gelbooru + 8k AI-generated images.

・UNet lr= 5e-6 ~ 3e-6

・Text Encoder 1 Lr = 3e-6 ~ 1e-6

・Text Encoder 2 Lr = 2e-6 ~ 7e~8

To prevent excessive training, the dataset categorized by style sets repetition numbers based on the amount of data.

Prompting Guide

・1girl/1boy/2girls..., characters, copyright, style, general tags, rating, score_9, score_8_up, score_7_up.

Negative Prompts

・score_4, score_5, score_6, source_pony, source_furry, monochrome, realistic, rough sketch, fewer digits, extra digits

Score tags are adjusted so that, average anime illustrations are generated, without the aesthetically tuned styles like in v1.0.

To increase detailing or change styles, you can use prompting similar to 'NovelAI' or use 'lora'.

Some artist tags seem to work. When using artist tags, write the score tags at the end.

Example

v1.0

Introduction

This model is finetuned from Pony Diffusion V6 XL.

Trained by SFW and NSFW images scraped from Danbooru, Gelbooru.

Tagging follows the template of Pony Diffusion.

score, 1girl/1boy/2girls..., characters, copyright, style, general tags, rating

Negative Prompts

score_4, score_5, score_6, source_pony, source_furry, monochrome, 3d, photo, hyperrealistic, realistic, rough sketch, fewer digits, extra digits, signature, artist name

Score tags have been made clearer.

  • score_9: high quality illustrations

  • score_8_up: realistic texture

  • score_7_up: anime-like

Although no training focused on specific characters, some characters may have been learned.

License

Fair AI Public License 1.0-SD

Support☕ https://ko-fi.com/sfa837348

投稿者

前の画像
CyberRealistic - v4.2
次の画像
Caravel Painted Style - v2.0

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

Pony

モデルバージョン

v1.0

モデルハッシュ

7ad8ce957e

作成者

ディスカッション

コメントを残すには log in してください。

「PD for Anime - v1.0」による画像

基本モデル画像