<h3 id="version-2">VERSION 2</h3>Dataset now expanded to:<ul><li>743 1girl images</li><li>210 1boy images</li><li>162 group images (2girls, 3girls, 2boys, 1boy &amp; 1girl, etc.)</li><li>79 still-life subjects and animals</li><li>104 images of detailed scenery</li><li>13 miscellaneous images</li></ul>Usage remains the same, see sample images for prompts and strength comparisons. All showcase images are made in Illustrious v1.0.<h3 id="version-1">VERSION 1</h3>A LoRA trained on a collection of images that were either:<ul><li>Trending on PixAI over the last few days</li><li>Have come top in events/competitions</li><li>Were top on detail or aesthetic focused LoRA</li></ul>This model isn't trained for a specific style/composition, although it may be biased towards images that PixAI users consider good. Recommended weights 0.2 - 0.8 (see sample images for examples of different weights).The model is trained to activate when it sees the token:<pre><code>trending_on_pixai</code></pre>this model is intended to be used with any baked-in quality tags in the base model.This model works both on human and non-human targets, with a dateset comprising of:<ul><li>553 1girl images</li><li>130 1boy images</li><li>115 group images (2girls, 3girls, 2boys, 1boy &amp; 1girl, etc.)</li><li>46 still-life subjects and animals</li><li>78 images of detailed scenery</li></ul>The first set of sample images are generated using the base Illustrious-v1.0, and this is the model that it was trained on. It works well with other finetunes. All sample images are generated using a simple negative, so that the effects of this LoRA are more obvious (the LoRA was not trained on any negative tags):<pre><code>worst_quality, low_quality, bad_anatomy, bad_hands, text</code></pre>The last five images in the showcase are generated using the one of the most popular finetunes of Illustrious (WAI v14) with a full negative prompt for illustrative purposes.

Trending on PixAI - People's Works

trending_on_pixai_peoples_works-v1-step00004800.safetensors

v1.0

v2.0

A LoRA trained off of works which were trending on PixAI over the last few days as well as those that placed top in competitions etc. At low weights it adds a subtle polish to images generated using Illustrious.At higher weights it also adds more details and finer linework.All non multi-image samples are at strength = 0.3 to strength = 0.6.

Files with SHA256: 4a872a3ca1e4e1d30db44711a7a1ef6f696e2c130af71fbeb1ae2e93191d5008