Trained 1024x1024 on 600+ high resolution sharp images of women opening mouth wide, sticking out tongue, showing uvula, displaying teeth, roof of mouth etc.
Most realistic samplers are like DPM++ 2M or DEIS or SD Forge - Flux Realistic (slow) (Scheduler: Beta ), the latter gives amazing results!
Guidance / (distilled) CFG between 1,8 and 2,5, Keep it low for realism!
Lora strength between 0.7 and 1
V2.x has a different, extended, training set and configuration, following prompts better yet with different image results from V1.x, more variety.
V1.2 is the final from V1 training set and config, producing excellent image quality, but not following prompts as well and less variety in output
Description
FAQ
Comments (19)
something is missing in your recipe: a few drops of cum.
congrats. i knew someone would go there
man of culture, go on!
i am sure you can add them yourself :-)
Another lora, or just describe it without describing it directly. :D
If you're able to make it can we please get a Pony XL lora version of this?
ah, do you think that will be better performing than the Flux and why?
@jhnprst2150 Well for me and those who also have potato quality computers, yes.
lol
@MaryElisabethPhilips If I score enough buzz and civitai support Pony training, I may actually try the online trainer. I am not going to do it on my own computer, this Flux lora took my own potato like 3 full days :-/
@MaryElisabethPhilips If you want realism then it should be trained on XL and not on pony.
anyone tried OpenFlux yet?
@yofoton174609 not sure what would be benefit for inferencing/generating images?
@jhnprst2150 maybe pony could make an uncensored version of it and we would get flux-booba :P
@yofoton174609 please post a serious sample prompt of what you like to see xxx/nswf like using this tongue lora, so I get an idea.
I would love a XL version of this (not pony), if you need buzz I can givezz :)
@jaume curious what would a SDXL version bring that Flux or Pony does not?
@jhnprst2150 I can't run Flux, Pony lacks realism... my pc is a potato too
@jaume ok can you DM me, i am fine with running the same extensive image training set (600+ super hires) for SDXL but you need to cover the cost of the training so we need to discuss the parameters