Aesthetic Quality Modifiers - Complete
v3.0 [noobai-v-pred-1]
motimalu
Aesthetic Quality Modifiers - Complete
Training data is a subset of all my manally rated datasets with the quality/aesthetic modifiers, including only the masterpiece, best quality , or very aesthetic tagged images (5332 total).
Recommended to use this LoRA over others in the Aesthetic Quality Modifiers Collection.
As the largest dataset, it will take some time to train on multiple base models - currently training on Illustrious base
Popularity
Info
Version v3.0 [noobai-v-pred-1]: 1 File
About this version: v3.0 [noobai-v-pred-1]
Trained on NoobAI-XL (NAI-XL) V-Pred 1.0-Version
Included addtional ~2000 (now 7273 total) newly rated images.
Training/tagging updates:
change
min_snr_gammafrom 5 to 0should produce closer lighting/blacks to base model
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: 14 Versions
Go ahead and upload yours!
