詳細
おすすめ
v2.0 (Fp16/Pruned)
v1.0
Ikigai 2.5D

Ikigai 2.5D

17.4K
163
9
#アニメ
#ベースモデル
#セミリアリズム
#2.5D

Does what you want. Does what you love. Does what you're good at! (except hands)
Your Ikigai!


I made this mix because I really love fine details provided by some models, but didn't want be bound to a certain look for faces, lighting, etc.

This model focuses mainly on 2.5D and semi-realism, and handles loras, TIs, long/short prompts, and everything in between very well!


V2:

Now with even better lighting, more detail, and no loras needed to achieve the look!! This iteration plays a lot nicer with Textual Inversions without the need of realism, detail, or artist loras, but they're still welcome!

Added the following models to the mix

WWColor
Real Moon

V1:

My usual settings:
Sampler: DPM++ 2M Karras
Sample Steps: 20-35
Upscaler: ESRGAN_4x
Deniose: 0.5
CFG: 5-9

Model has no VAE baked in, I personally use Graprfruit-VAE

By no means is this law, feel free to experiment and I'd love to see your results!!

For inpainting, I generally limit to Only Masked to 800 x 800 or lower and 0.5 denoise, as it will start to get a little too detailed otherwise. You shouldn't need to change your prompt at all when inpainting faces to get a good result. This was a goal of mine, as I prefer not to have to do any extra steps in my workflow if possible.

This mix comprises of:
MajicMix Lux
MIX-Pro-V4
Babes 2.0

For the semi-realism look in a couple of the example images, I HIGHLY recommend the lora below at a weight of 0.1-0.2:
Danni-2D (looks to be removed, but any lora that would add realism to models like AOM3)

Model also plays reaaaally well with 2D artist style loras like DevilHS, Gopher, SamDoesArt, etc. and will often help with the hands issue.

All example images have no post-work beyond inpainting and SD upscale within the webUI.

翻訳を表示

評価とレビュー

4.8 /5
0 件の評価

まだ十分な評価やレビューが集まっていません

G
お知らせ
2024-06-18
モデルを公開
2023-06-21
モデル情報を更新
モデル詳細
タイプ
Checkpoint
投稿日時
2023-06-21
基本モデル
SD 1.5
バージョン紹介

Fp16

Pruned

許可範囲
モデルソース: civitai

1.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します

2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証

創作許可範囲
オンライン画像生成
統合
ダウンロード
商用利用の許可範囲
生成された画像は販売または商業目的での使用
モデルの転売やモデル統合後の販売
QR Code
SeaArt Appをダウンロード
モバイルでAI創作の旅を続けよう