<h1 id="heading-835">PDXL Version</h1><p>Not much to say here other than it's a retrain of an old model. If you're curious about the last image it was made by accident while trying to get non-portrait shots. I just included portrait in the negative and got some weird burnt outputs, but they also looked cool so I included one for reference. Anyway, enjoy!</p><h1 id="heading-836">SD 1.5 Version</h1><p>Another old LoRA I never posted. Sort of painterly?</p><p>Note: The "nipples" negative should be unnecessary. It was left in from before.</p><h2 id="heading-15">Why doesn't my output look like yours?</h2><ol><li><p>Check the negatives in my examples. Do you have those embeds?</p></li><li><p>I used !ADetailer because it's just a set and forget quality bump.</p></li><li><p>The images were genned at 512x768 then upscaled 1.5 times using 8x_NMKD-Superscale_150000_G with denoising 0.45. You can find it with a quick Google. Note that this upscaler is non-deterministic from my testing so your images may vary slightly. (Check the bottom of this post for info on the cover image.)</p></li></ol><h2 id="heading-4542">Settings and Training:</h2><p>Trained on Anything v3<br />Genned on Anything v4.5<br />LoRA weight 0.8</p>

Files with SHA256: 60381588340ade3bfd2ddec5cec112dd882cf4638d3c68b08b07e3aab01cb1a9