this post was submitted on 06 May 2024
20 points (100.0% liked)

Stable Diffusion

5018 readers
7 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
db0@lemmy.dbzer0.com
Even_Adder@lemmy.dbzer0.com
20
Training Loras - Is SDXL still the best? (poptalk.scrubbles.tech)
submitted 1 year ago by scrubbles@poptalk.scrubbles.tech to c/stable_diffusion@lemmy.dbzer0.com
5 comments fedilink hide all child comments
 

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?

you are viewing a single comment's thread
view the rest of the comments
[โ€“] istanbullu@lemmy.ml 0 points 1 year ago* (last edited 1 year ago) (1 children)

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.

[โ€“] scrubbles@poptalk.scrubbles.tech 1 points 1 year ago

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?