Hey folks, I’ve been training Loras now for a while, and have some scripts I really like that I’ve been working with. However, I realized I haven’t been keeping up lately, so, is SDXL still the best for Loras? And by that I mean before with 1.5 and standard SDXL is the most accurate quality I’ve received.
My Loras seem to work fine with Lightning and Turbo models, but is there anything else I should look into? Any major things that you’ve changed in the last 6 months to your trainings? Is sdxl_base the best basemodel to train off of?
Comparing base model to base model I think Cascade is quite a lot better than SDXL, but …and it’s an enormous but… It seems to have been shunned by the community.
Maybe nobody with resources to do training is interested in a model with commercial restrictions, or the multi-model flow was just too different for people. Not sure, but the output of the base model can be really nice. Not always, but I find the biggest errors are people taking on a painterly/waxy appearance rather than the arm turning into a leg body horror you can get with SDXL. I think the “compressed” Stage C works to keep the composition together across the whole image more.
Thanks! Ill have to try it out to see what it takes to train, but their Numbers do look nice
I think Cascade doesn’t have the ecosystem that SD15 and SDXL have built in the last year. It might be a better model on fundamentals, but that doesn’t help if the ecosystem is not there.
I think SDXL (plus optionally lightning) is still the best model to use until SD3 comes out for real.
I haven’t used the base model in ages though. I usually go for RealVis or one of DucHaiten’s finetunes in CivitAI.
I’ve been using dreamshaper lightening for a while, dmehats your go to model for realism if not sdxl? Not for training now, but for all around use?