Spaces:

lnyan

/

stablediffusion-infinity

like 823

Sleeping

This has been a fun and useful tool to play around with, I'm just wondering if it's possible to update the AI model to use RealVisXL 3.0 since I've noticed that when trying to paint (extend) body parts that the results can often be distorted limbs. I've used RVXL 3 in other huggingface demos and while not perfect, it seems to generate more consistently non-distorted output.
Thank you!