<h1 id="aesthetic-quality-modifiers-complete-vn696gubc">Aesthetic Quality Modifiers - Complete</h1>Training data is a subset of all my manally rated datasets with the quality/aesthetic modifiers, including only the <code>masterpiece</code>, <code>best quality</code> , or <code>very aesthetic</code> tagged images (7273 total).Superset and final of models in the <a target="_blank" rel="ugc" href="https://civarchive.com/collections/6456031">Aesthetic Quality Modifiers Collection</a>.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):<pre><code>{{tags}}
masterpiece, best quality, very aesthetic</code></pre>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: <a target="_blank" rel="ugc" href="https://civarchive.com/posts/11457095">https://civarchive.com/posts/11457095</a>

Aesthetic Quality Modifiers - Complete

Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/833294/noobai-xl-nai-xl?modelVersionId=1190596">NoobAI-XL (NAI-XL) V-Pred 1.0-Version</a>Included addtional ~2000 (now 7273 total) newly rated images.Training/tagging updates:<ul><li>change<code>min_snr_gamma</code> from 5 to 0<ul><li>should produce closer lighting/blacks to base model</li></ul></li><li>tag <code>nsfw</code> <code>explicit</code> with imgutils anime_rating</li></ul>Previews are generated in Forge with DynamicThresholding (CFG-Fix) Integrated enabled, settings.<pre><code>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</code></pre>

noobai_vpred_1_aqm_complete_v3.safetensors

v3.0 [noobai-v-pred-1]

v3.0 [animagine v4]

v2.0 [noobai-v-pred-1]

v1.0 [Illustrious]

v1.0 [noobai-e-pred-1.1]

<h1 id="aesthetic-quality-modifiers-complete-vn696gubc">Aesthetic Quality Modifiers - Complete</h1>Training data is a subset of all my manally rated datasets with the quality/aesthetic modifiers, including only the <code>masterpiece</code>, <code>best quality</code> , or <code>very aesthetic</code> tagged images (7273 total).Superset and final of models in the <a target="_blank" rel="ugc" href="https://civitai.com/collections/6456031">Aesthetic Quality Modifiers Collection</a>.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):<pre><code>{{tags}}
masterpiece, best quality, very aesthetic</code></pre>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: <a target="_blank" rel="ugc" href="https://civitai.com/posts/11457095">https://civitai.com/posts/11457095</a>

Files with SHA256: be40d33a5d5908bb1033a30ebaa9391958a0a88e6d39a174a4fd315927cda413