Sign In

better faces cultures sdxl/FLUX

1.0k
20.2k
743k
418
Verified:
SafeTensor
Type
LoRA
Stats
360
54
Reviews
Published
Sep 5, 2024
Base Model
Flux.1 D
Usage Tips
Strength: 0.8
Trigger Words
aborigines african arabian arctic brazilian chinese european havaiian japanese mongolian nordic russian western
Hash
AutoV2
BB05C3E1F4
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.

*** left *** >>>with my lora<<< *** left *** --- --- *** right *** >>>with out (the puppy face)<<< *** right ***

i found its more amateur not that model_flux like

in better faces I tried to include many cultures/ethnic, 11-if i remeber, with old and young content, at the moment only woman

-> it listen to __yo -> 20yo, 30yo, 40yo

V........... see below ..............V

try my other face expression lora, if you use it with only 0.4(without trigger) you have much more real one

https://civitai.com/models/151594?modelVersionId=323528



so carefule, it improves and needs less steps (for portrait ~12), so play with it ...

i want real faces so no symmertrie but natural skin :)

ATTENTION -> weight correction 0.3-0.9 results with 25 steps DPM++2M SDE Karras almost the same images as without and 70 steps

FLUX -> Euler and DDIM -> 12-20 Steps

Trigger is not essential but useful for the culture ! ;)

-

FLUX -> knows mature, 40yo and young, 20yo ... reduced bokeh, for higher weight above, tryed to learn faces without any jewelry so you should add, also add background

pony_weak -> better for closeups, works not that good with complex prompts, not only 1girl, and call background

pony_strong -> works better with more complex prompts, not only 1girl, and call background

face enhancer_v3 -> more strong in close-ups and pls register my prompts ;)

face enhancer_v2 -> much more smother and better ;)

-

multifacesv3 -> (group, crowd, many faces), it only generates more people, distant faces are still not so good ; weight (0.3-0.8)

-

multifacesv2 -> (trigger: "number" faces)

And please its for the basemodel! so you can try or merge it and finde out ;)

i used also copax and juggernaut that is already not that bad at small faces so may you dont need it!

-

multifacesv1 -> (trigger: group, faces) combine with my v3, try and tell me ;)

-

-> all in all i suggest "adetailer" or refiner for small faces !
https://civitai.com/articles/5002/face-swap-with-adetailer-and-reactor


SDXL new VAE (2023.07.26) is quite better than older ones for faces,

but try my lora and you will see often more real faces, not that blurred soft ones ;)



Hints:

  • pls, almost no negative prompt is necessary!

see my article:

https://civitai.com/articles/1890/better-faces-lora

https://civitai.com/articles/1826/sdxl-prompts

All SFW!