Concept LoRA based on "Venus Body" type, this need no presentation if you have used mnemosynekotorin's LoRA for SD1.5

My version of this LoRA seems to work fine on most anime SDXL models, this was trained on 1052 images and aims to produce thick thighs and wide even if you don't increase size.

This has a trained Text Encoder, please remember to test it as well, all preview images were with TE strength 1.

if you have a dataset that might increase this LoRAs "effectiveness" please do tell me how to reach you.

Caveats/quirks/issues

1. Has a trained Text Encoder so I truly don't know how this will behave with some models that seem to have a trained TE (For example it works with Animemagine XL but has a ton of issues)

2. Known trigger words for size, "flat " "" "" ""

3. Known trigger words for and thighs size, "small " "small thighs" "wide " "thick thighs" "huge " "huge thighs" "gigantic thighs" "gigantic "

4. Increasing sizes will increase the size for thighs and , sorry.

5. Using "slim waist" "slender waist" "small waist" will reduce the size of the waist, and , please experiment with it.

6. Conversely, "plump" and "plump belly" will increase all 3 sizes as well.

7. Can generate kinda muscular looking females, arms, thighs, abs, and back mostly

8. KINDA works with DreamShaperXL, but haven't tested on other realistic models, sorry.

9. Most of the previews are made with ReproductionXL v3.1, again, sorry.

10. Used SDXL v1.0 with v0.9 VAE as base for this model.

11. Since SDXL has some issues with I tried training without much content. That's why you'll see , slip, and in the NEGATIVES, since the dataset used for training had images with those, and putting these in negatives seems to reduce some sudden creeping out of nowhere.

12. For whatever reason using wide and thick thighs will sometimes, produce a image like it had "" tag, dunno why, but seems to happen with these tags, using a "facing forward, facing front" or the like, solves it, again, dunno why.

13. Expressions are mild but that's due to the lack of 'em in the base models.

These were the custom nodes installed in my ComfyUI installation

This is a bit outdated but I've included Adetailer for faces in the full workflow included with the images

Has two sets of upscale workflows just connect the node you want to run, both uspcale with model, and latent upscale + model, you can connect both to a Adetailer for the face, the full workflow is ready

If you like what I do please consider supporting me via Ko-fi, training SDXL is insanely expensive both hardware-wise and time-wise.