Available for SD1.5, SDXL and Pony! -> check version
I know there is a lot of similar LoRAs. However, this is my approach and I hope you like it. There will be three version: lift, pull and spread.
This LoRA is based on a set of 38 photo samples and trained with the PicX real model. It works with different views and poses, as well as realistic and non-realistic models. Use a strength between 0.6 and 0.8 for best results.
Don't forget to share your images, I'd love to see what you have created. And if you have a few minutes left, make sure to have a look at my other LoRAs. Happy prompting!
Description
FAQ
Comments (2)
Not sure why - but this Lora makes the photo only show the chest. ie: cuts off the head out of frame.
edit: nevermind, adding head out of frame to negative fixes this
Hi. Thanks for the feedback. To get the LoRA to interfere less with faces, I usually cut off the heads in the sample images. Glad you found a work-around.