SD 1.5 VERSION: https://civarchive.com/models/274183/facesitting-sd15-girl-sitting-on-face
v1.1
Optimized the training parameters to make the model much smaller in size with the same dataset.
*All of the preview pictures for v1.1 can be imported into ComfyUI to see exactly how they were generated. No extra embeddings, upscalers or detailers! Just a hi-res fix to get to a reasonable resolution.
I highly recommend extra embeddings, upscalers, and detailers to get the most out of your composition!
A LoRA trained on high quality images to produce satisfactory facesitting images in SDXL. Multiple angles supported, but results may vary depending on the base model and strength.
Clip Skip: 2
Optimal Strength: 0.5-0.8
Trigger word: facesitting
Add other terms as well such as "sitting on chair" or "kneeling on a bed".
The LoRA attempts to take over any sitting, kneeling, or squatting actions. Adding the term "boy lying on floor" or "boy sitting on chair" may help if the male is not appearing. If the male is "sitting" against the object, the LoRA should re-arrange the scene to make his face the seat.
Description
Initial Release
FAQ
Comments (10)
OHH HOLY :( its only for xl... can u do the 1.5 version too?? Nice work, love that !
https://civitai.com/models/274183
Here you go :)
Trained on the same dataset but with the SD 1.5 base model
@Questionable_Models MY MAN!
um how did the lora end up being 1.7 GB ?
i've never seen a lora exceed 1 GB before
I most likely set the network dimensions a little too high during training when I was tweaking the settings. I'll see if another run on a lower number can produce a smaller file with similar results.
just wait till you see lora's bigger than the base model.
I just released v1.1 which is another round of training on the same dataset with the same parameters, but with half the network rank. The file size is much smaller with seemingly the same quality. :)
Hi dude, how about make a loar for the concept "face in ass"~PLZ!
Thats a great idea! Ill have to see if I can find a high quality dataset!