<h1 id="heading-6">Update:</h1><p>Pony. Should actually work consistently on Pony and AutismMix now. Apparently already works well enough on landscape</p><p></p><h2 id="heading-7">Update for XL v1.0:</h2><p>oh yeah XL is a thing</p><p>also chairs</p><p>also recommended weight still 1.0</p><p></p><h3 id="heading-141">Update for v3.5:</h3><p>nothing much except made the guy actually show up in the frame more consistently</p><p>also chairs</p><p></p><h3 id="heading-396">Update for v3.0:</h3><p>should have good character and style LoRA compatibility all around now</p><p>currently tailored to images of width 512 of only (512x768 etc)</p><p>adding the tags <strong>girl on top </strong>and <strong>straddling </strong>appears to improve generation consistency somewhat, but I haven’t done extensive tests on it</p><p>Probably better to use weight 1.0 for this one</p><p></p><h3 id="heading-397">Previous versions:</h3><p></p><p>tested on anything v4.5, corneosu7thheavenmix, and AOM3</p><p>recommended weights: 0.7-0.8</p><p>compatibility with character LoRAs: case by case basis. Just put the intended weight of whichever of them for the best chance that it works out</p><p>optional tag for hugging and more visible genitals</p>

Upright straddle sex front view

<p>hopefully reduced overburnt images and increased compatibility with character and style LoRAs due to being trained from a bigger dataset this time.</p>

Files with SHA256: 620d7dba0ee3724c72b992db520d9825dee4beb714d6d6a3680b6e8d13b311d7