Only for anime models!Make clothes less tight around pregnant belly if possible while minimizing style change.has small chance to add clothing covering the belly.Can work with pregnant belly sliders.v3Recategorize lora to SDXL, following NoobAI XL category, still can work with it's merges that categorized as illustrious (not tested on pure illustrious finetunes).v3 is trained with much less dataset, mostly to remove image with folded fabric under the belly.also text encoder isn't trained anymore, no actual effect because i don't introduce new trigger.v3 soft is v3 hard without in8 layer, make it less influence composition of the image.v2Add more images from danbooru as dataset to force draping on clothes.v1Trained with AI generated images.using kohya_ss with settings from blora_for_kohya.The training focused on in8 (layout), out0 (content), out1 (style) in the UNet, and layer0 of clip_2 (text encoder).I use slicer to use only content, layout, and text encoder components, which is reflected in the 'clte' naming.using this will decrease the dataset style influencing the generated image.