Dont waste your buzz, I dont do civit stuff. Just sharing my own personal loras Ive been experimenting with. <hr /><h3 id="nsfw-upscale">Nsfw Upscale</h3>Edit lora: 1 input imageSpecifically for high frequency details. Trained on high quality nsfw explicit images.Trigger: <code>enhance</code>Edit: workflow is outdated, will update it soon, check comment by other user below<s>Required: Add the LTXVpreprocess node, it adds a predictable artifact to the image, that this lora was trained on to fix (native comfy node). ImageScaleToTotalPixels to --&gt; 2MP.</s><s>There should be a workflow embedded in the image. Pretty straightforward though</s> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/83dcf731-226f-42ad-9609-8a3ccd625b0d/original=true/83dcf731-226f-42ad-9609-8a3ccd625b0d.jpeg" /><hr /><h3 id="nsfw-transfer-head">Nsfw Transfer Head</h3>Edit lora: 2 input imagesV1A somewhat better head swap lora for nsfw. Female centric. Trained on various viewing angles with some facial expressions. But it seems that klein just struggles with understanding erotic expression in general soo.. dont expect too much.Trigger: <code>transfer head</code> Full caption it was trained on: <code>transfer head into the same position and location with the correct size while retaining the original emotion and expression</code>V1.1Removed some junk from dataset and retrained with better paramsTrigger: <code>transfer head</code>Actually found that mentioning expression or emotion is bad because it triggers the base model to override the lora with dumb shit<hr /><h3 id="nsfw-forbidden-lora">Nsfw Forbidden Lora</h3>Edit lora: 1 input imageIts a lokr. Old one from when I was playing with lokr's. Female centric. Trigger is in the caption details.

CRZ Klein9b Loras

Files with SHA256: 836b214974eba57987ce73f677b2694a974a4b61f6b8dffac4b93263895de564