Available for SD1.5, SDXL and Pony! -> check version
This LoRA is based on a set of 39 photo samples and trained with the PicX real model. It works with different views and poses, as well as realistic and non-realistic models, but it seems to have some issues with anime checkpoints. 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 (4)
For other lora I advise weight to 1 and add for stability in some cases take off bra,lift bra
thank you for great work
Can't get results with face visible
Hi. Did you try to use a specific focus (portrait, wide shot) and to further describe the face?