models/Aesthetic Quality Modifiers - Masterpiece - v2.3 [noobai-v-pred-1]

Aesthetic Quality Modifiers - Masterpiece - v2.3 [noobai-v-pred-1]

|
12/9/2025
|
10:42:05 PM
| Discussion|
0
A large lavender-colored tree stands against a sunset sky with a silhouette of a girl and a cat nearby in a surreal fantasy scene.
A chubby panda with big black eye patches and a tiny chef hat grinning while preparing a chocolate cake in a colorful kitchen.

Recommended Prompts

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

1girl, best quality, masterpiece, very aesthetic, absurdres <lora:noobai_vpred_1_masterpieces_v23:1>

Recommended Negative Prompts

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

Recommended Parameters

samplers

Euler

steps

30

cfg

10

resolution

832x1216

other models

noobai_vpred_1_masterpieces_v23 (ce9764dca3eb), noobaiXLNAIXL_vPred10Version (bb85cf4f43), noobai_vpred_1_star_trail_v1 (383a8f683823)

Recommended Hires (High-Resolution) Parameters

upscaler

upscaling, adetailer, DynamicThresholding, FaceDetailer, 4x-UltraSharp

upscale

2

steps

10

denoising strength

0.3 - 0.35

Tips

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

Refer to 'About This Version' on the base model pages for specific workflow and training information.

Previews are generated using Forge with upscaling and adetailer.

A ComfyUI workflow reference for Noobai V-Pred with DynamicThresholding, Upscaling, and FaceDetailer is available.

Version Highlights

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

Included many newly rated images and small training/tagging updates:

  • changemin_snr_gamma from 5 to 0

    • should produce closer lighting/blacks to base model

  • change very awa tag back to very aesthetic

    • reverted this change from previous version v1.0

  • tag nsfw explicit with imgutils anime_rating

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

A ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095

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

Previous
CyberRealistic Pony - v12.7 Alt
Next
Scrat - Ice Age - IL - V1

Model Details

Model type

LORA

Base model

NoobAI

Model version

v2.3 [noobai-v-pred-1]

Model hash

d7b5c187bd

Trained words

masterpiece, best quality, very aesthetic

Creator

Discussion

Please log in to leave a comment.