Aesthetic Illustrious

CHECKPOINT
Original - TenStar Fund


Updated:

This is a prototype model based on Illustrious XL V2.0 Stable that is being additionally learned and tuned to develop a base model that will be the basis for upgrading ToxicEchoIL or another style of model.

It is being tuned primarily for the purpose of improving backgrounds, lighting, textures, and portrayal of people.

Basically, the full fine tune is done at Illustrious' native resolution of 1536, and some LoRA may be used for adjustments.

The added versions are not necessarily better than the newer versions, but rather various adjustments and differences in the basic style, so please use the version you prefer.

Illustrious XL V2.0 Stableをベースに、ToxicEchoILのバージョンアップ、または別スタイルのモデルの基本となるベースモデル開発のために追加学習、チューニングしているプロトタイプモデルです。

主に背景やライティング、質感、人物描写を改善する目的で調整を行っています。

基本的にはIllustriousのネイティブ解像度1536でファインチューンを行い、調整用にいくつかLoRAを使用する場合もあります。

追加されるバージョンは新しい方が優れているといるわけではなく、様々な調整や基本スタイルの違いなどですので、好みのバージョンをお使いください。

----------------------------------------------------------------------------------------------------

Recommended settings:

*Basically conforms to the recommended settings of the original model

Rating tags

Safe content: safe, general

Sensitive content: sensitive

Explicit content: explicit, nsfw

Must include tags:

masterpiece, aesthetic, extremely aesthetic, newest, very vibrant colors,

Negative prompts:

lowres, bad anatomy, bad hands, text, error, missing fingers, extra digits, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name,

Image Size: 1024 - 1536px (896x1152, 1152x1536, etc. )

CFG Scale: 2 to 8

Sampler: Euler a

Sampling steps: 25 to 30

Hires. fix:

Upscale by: x1.5 to 2.0

Upscaler: ESRGAN_4x

Denoising strength: 0.4

Hires steps: 15

ADetailer: On

----------------------------------------------------------------------------------------------------

おすすめ設定:

※基本的にはオリジナルモデルの推奨設定に準拠します

レーティングタグ

安全なコンテンツ:safe, general

センシティブなコンテンツ: sensitive

露骨なコンテンツ:explicit, nsfw

必須タグ:

masterpiece, aesthetic, extremely aesthetic, newest, very vibrant colors,

ネガティブプロンプト:

lowres, bad anatomy, bad hands, text, error, missing fingers, extra digits, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name,

画像サイズ: 1024~1536px (896x1152, 1152x1536, etc. )

CFG Scale: 2 ~ 8

Sampler: Euler a

Sampling steps: 25 ~ 30

Hires.fix:

Upscale by:x1.5~2.0

Upscaler: ESRGAN_4x

Denoising strength: 0.4

Hires steps:15

ADetailer:ON

Version Detail

Illustrious
This model is based on Illustrious V2 Stable and fine-tuned to an easy-to-use style. Because it is a base model, it is intended to be used for specifying art styles and LoRA use. Illustrious V2 Stableをベースに使いやすいスタイルにファインチューンしたモデル。ベースモデルのため、アートスタイルの指定やLoRAの利用などを想定しています。

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.