Download
1 variant available
455
3.3K
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Trained on high resolution sharp images of amateur female women (real photographs not ai) opening mouth wide, sticking out tongue, showing uvula, displaying teeth.
Use this Lora to
enhance the quality, texture and reality of mouths, teeths and tongue elements of female
it also effects the skin quality, it add/keeps skin pores but added elements like sweat etc. may be dampened
Strength: 1.5
My own workflow for best reality pictures:
Resolution: 1024 - 1536
Steps (klein distilled): 6 - 8 instead of recommended 4 , more steps tend to enhance/fix the anatomy like fingers etc. a weakness of Flux
Sampler: Euler (or Euler A) - these are fast and produce good realistic human skin and anatomy
Prompt addition: Amateur saggy photo. True-to-life photographic scene. Skin pores visible, no freckles or moles. Natural skin. Lips with detailed texture, subtle natural cracking, and slight moisture. Perfect teeth.
Extra recommended Loras: Lenovo Flux Klein 9B on 0.65, Snofs V 1.3 (NSFW helper) on 0.75
Extra recommended postprocessing: Z-Image Turbo (+ same lora ZIT version: https://civitai.red/models/2188629/female-tongue-mouth-and-teeth-z-image) , 9 Steps, Denoise 0.10 - 0.15, Sampler Euler, Scheduler Beta. Feed latent after latent upsampling using VAE on 1.25X. Repeat twice.
Note the samples in my gallery are all produced with the 'extra recommended loras' and the 'extra recommended postprocessing'.
You will not get these results using this Lora only, it's effect on its own is more marginal.