モデル/Aesthetic Quality Modifiers - Masterpiece - v1.0 [noobai-v-pred-1]

Aesthetic Quality Modifiers - Masterpiece - v1.0 [noobai-v-pred-1]

|
8/23/2025
|
10:39:16 AM
| Discussion

推奨プロンプト

{{tags}} masterpiece, best quality, very aesthetic

1girl, dark, masterpiece, very awa, best quality, absurdres <lora:noobai_vpred_1_masterpieces_v1:1>

推奨ネガティブプロンプト

(worst quality, low quality, sketch:1.1), error, bad anatomy, bad hands, watermark, ugly, distorted, censored, lowres, abstract, signature, bkub

推奨パラメータ

samplers

Euler

steps

30

cfg

10

resolution

832x1216

other models

noobai_vpred_1_masterpieces_v1 (e678d649f47c), noobaiXLNAIXL_vPred10Version (bb85cf4f43)

推奨ハイレゾパラメータ

upscaler

4x-UltraSharp

upscale

2

steps

10

denoising strength

0.3

ヒント

LoRA works best applied to the base models on which they are trained.

Use the recommended prompt structure with quality tags at the end.

Reference ComfyUI workflow for Noobai V-Pred with DynamicThresholding, Upscaling, and FaceDetailer.

バージョンのハイライト

Trained on NoobAI-XL (NAI-XL) V-Pred 1.0-Version

With the kohya_ss dev branch, v_paratemization ,zero_terminal_ssr enabled, and noise offet set to 0.

Included some newly rated images and small updates to match the noobai tagging:

  • by {artist} -> artist:{artist}

  • very aesthetic -> very awa

Previews are generated in Forge with DynamicThresholding (CFG-Fix) Integrated enabled, settings:

dynthres_enabled: True, dynthres_mimic_scale: 7, dynthres_threshold_percentile: 1, dynthres_mimic_mode: Half Cosine Down, dynthres_mimic_scale_min: 1, dynthres_cfg_mode: Half Cosine Down, dynthres_cfg_scale_min: 3, dynthres_sched_val: 1, dynthres_separate_feature_channels: enable, dynthres_scaling_startpoint: ZERO, dynthres_variability_measure: STD, dynthres_interpolate_phi: 1

クリエイタースポンサー

For Noobai V-Pred, a ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095

Subset in the Aesthetic Quality Modifiers Collection

Aesthetic Quality Modifiers - Masterpiece

Training data is a subset of all my manually rated datasets with the quality/aesthetic modifiers, including only the masterpiece tagged images.

Subset in the Aesthetic Quality Modifiers Collection.

ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information.

Recommended prompt structure:

Positive prompt (quality tags at the end of prompt):

{{tags}}
masterpiece, best quality, very aesthetic

Generation Settings:

Previews are generated in Forge with upscaling and adetailer.

For Noobai V-Pred, a ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095

前の画像
SketchPalette - v1.0
次の画像
YFG Spy World 50s - v10 [Flux] *** UPDATED *** - v10.0

モデル詳細

モデルタイプ

LORA

ベースモデル

NoobAI

モデルバージョン

v1.0 [noobai-v-pred-1]

モデルハッシュ

feea184c0a

学習済みワード

masterpiece, best quality, very awa, absurdres

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。