【Impermanence】Novel Promotion - niji Style - Ancient Beauty

0
0
0
0
AnimeGirlStyle Boost
最近更新:初回公開:
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info
Anime,Girl,Style Boost,LoRA,FLUX.1Image info

niji-Ancient Style Beauty:

Introduction to the selected Lora model: This model is trained based on the F.1-dev-fp8 base model, suitable for anime-style ancient beauty.

Recommendation: F.1 base algorithm model is sufficient.

Generation suggestion: F.1 base algorithm model - can be run on Libu online,

Sampling method: Euler

Lora weight: Recommended 0.4-1.6, generally 0.8

Recommended size: This model is trained on a 1024*1024 training set.

Iteration steps: 15-30, testing shows good results at 10 steps

Prompt word correlation coefficient: 3.5.

High-definition restoration: R-ESRGAN_4x+ Anime6B

Creative overview: How does the niji style perform under the F.1 model?

Trigger word: Animation style


ディスカッション

最も人気
|
最新
送信
もうすぐです
ダウンロード
(0.00KB)
詳細
タイプ
オンライン生成回数
0
ダウンロード
0
推奨パラメータ
推奨チェックポイントの組み合わせCheckpoint
なし
お勧めの重さ
0.8
CFG
3.5
VAE
なし

ギャラリー

最も人気
|
最新