Aesthetic Quality Modifiers - Masterpiece - v2.3 [noobai-v-pred-1]
推奨プロンプト
{{tags}} masterpiece, best quality, very aesthetic
1girl, best quality, masterpiece, very aesthetic, absurdres <lora:noobai_vpred_1_masterpieces_v23:1>
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
推奨パラメータ
samplers
steps
cfg
resolution
other models
推奨ハイレゾパラメータ
upscaler
upscale
steps
denoising strength
ヒント
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.
バージョンのハイライト
Trained on NoobAI-XL (NAI-XL) V-Pred 1.0-Version
Included many newly rated images and small training/tagging updates:
change
min_snr_gammafrom 5 to 0should produce closer lighting/blacks to base model
change
very awatag back tovery aestheticreverted this change from previous version v1.0
tag
nsfwexplicitwith 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: 1A 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 aestheticGeneration 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