Trigger words makes lora much stronger.
Recommended settings for Anima:
Sampler: er_sde | euler | dpmpp_sde_gpu
Scheduler: beta | linear_quadratic | simple
Lora Strength: 0.6-0.8 | Steps: 25 | CFG: 4Recommended settings for Krea2Turbo:
Sampler: er_sde | euler
Scheduler: beta | linear_quadratic | simple
Lora Strength: 0.8-1.4 | Steps: 8-10 | CFG: 1Recommended settings for MOSS-Image:
Base with 8step turbo lora
Sampler: euler
Scheduler: simple
Lora Strength: 0.8-1 | Steps: 8-16 | CFG: 1-3Description
FAQ
Comments (6)
what checkpoint?
How does your release even work?
Anima v1 followed by Anima v1 followed by Anima v2 followed by Krea2 followed by Anima v1 again?
But then if I click on them, the older ones by list order were actually released two days after the newer ones?
Yeah I kinda fumbled release of that one haha. I sorted them out the way they should be and work the best in my mind. I release more versions, because they all work differently. Well Done, Medium Rare and Raw are V1, trained the same way, just different levels of cook - that's why I try to include similar images on showcase. V2 was trained differently, but fell off for me, compared to V1 well done - but it's still good on it's own. I like giving people options, if that clears that part.
gorgeous lora,i love you,plz keeping doing and i'll support you forever. :D