It works.

#1
by javawock7618 - opened

Nice work. I'm using Ref2VA with FL2VA model and Ref-LoRA, and this 3step LoRA works really well. Thanks.

are you using 3 sampling steps?

This comment has been hidden (marked as Off-Topic)

are you using 3 sampling steps?

No, I mainly use 2-stage sampling. For example, I do 3 steps at 480p with this LoRA, followed by another 3 steps with Latent Upscale. I’ve published my workflow, so feel free to give it a try: Hugging Face workflow collection

Sign up or log in to comment