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

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

8/6/2025

7:09:13 PM

Related Keywords & Tags

aesthetic,aesthetic quality modifiers - masterpiece,anime,best quality,concept,lora,masterpiece,motimalu,noobai,quality tags,styles,v1.0 [noobai-v-pred-1],very aesthetic

Close-up of an elf with blonde braided hair, green eyes, holding a glowing magical staff, illuminated by golden volumetric lighting in a fantasy city background.

Konpaku Youmu stands alone on a forest path by a riverside under moonlight, holding a katana with autumn trees and lantern light around.

A fantasy elf girl with long blonde braided hair, green eyes, and pointed ears, holding a glowing staff in dramatic volumetric lighting.

Anime-style character Link in a green tunic and cap holding the master sword, illuminated by dramatic volumetric lighting with a luminous circular background.

Portrait of a cute femboy with short wavy bob-cut brown-blonde hair, freckles, and blue eyes, wearing a golden tiara and casual clothes, holding a plate with pudding topped with caramel sauce and smiling with eyes closed.

A fierce Oni girl with red skin and black horns in detailed Japanese armor, holding an engraved katana amid falling pink petals.

Recommended Prompts

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

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

Recommended Negative Prompts

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

Recommended Parameters

samplers

Euler

steps

cfg

resolution

832x1216

other models

noobai_vpred_1_masterpieces_v1 (e678d649f47c), noobaiXLNAIXL_vPred10Version (bb85cf4f43)

Recommended Hires (High-Resolution) Parameters

upscaler

4x-UltraSharp

upscale

steps

denoising strength

0.3

Tips

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

Use quality tags at the end of prompt for best results.

Preview generation can use Forge with upscaling and adetailer.

Reference workflows like ComfyUI with DynamicThresholding, Upscaling, and FaceDetailer can improve results.

Version Highlights

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

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