A generalized furry Anima diffusion model with more of the popular glossy ai-gen appearance. E621 concepts and natural language compatible prompting with text generation preserved.
WEAKLY recognized artist tags:
@accelo, @aycee, @bagelcollie, @baphypaws, @blitzpony, @braeburned, @budoti, @butterchalk, @chunie, @cobaltsynapse, @coffeesoda, @cometdragonite, @cytricacid, @dacad, @daftpatriot, @dagasi, @dingbat, @doodlemark, @edjit, @enginetrap, @fantine, @funkybun, @hinar miler, @hioshiru, @indexer, @jumpy jackal, @kashmere, @keffotin, @kenket, @keovi, @k1ngl30n, @letodoesart, @loimu, @mawmain, @meesh, @orlandofox, @reign-2004, @ruaidri, @sushiamazing, @tzarvolver, @waspsalad, @zackary911, @zaush
Additional artist tags recognized in version 2 and 3:
@cubi, @flipyart, @kabscorner, @latrans, @nopetrol, @panken, @zarckets
Additional artist tags recognized in version 4 and 4 10-step:
@allorexx, @jinxit, @leoncheetah, @mintyderg, @nicknak044, @sinz0ne, @tazara
Generation params: Sampler: euler Scheduler: sgm-uniform CFG: 4.5 Steps: 30-50 (38 recommended)
Description
FAQ
Comments (7)
Waiting wishing for a checkpoint that knows MLP characters more/better
I love furries
Hi~ What's the difference between versions 2 and 3?
More training on the e6 dataset to try and tighten up the artist styles a bit, also some negative merging of anime-centric loras to try and shift the style away from anime.
Fp16? Not bf16 for anima? What did you do differently?
Haha, selected the wrong precision as it looks like I've done for all my Anima materials. It is bf16.
@someyoungguy69 All good :3