----> left with my lora <----- , , , -----> right without and other steps <-----
so carefule, it improves and needs less steps, so play with it ...
i want real faces so no symmertrie and 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
Trigger is not essential but useful for the culture ! ;)
has a great impact on lower Sampling steps <30
if you use DPM++3M SDE Karras with 70 steps, you meight dont need my lora
-
multifacesv2 -> (trigger: "number" faces) combine with my v3, try and tell me ;)
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 "Face Editor" or refiner for small faces !
-
face enhancer_v3 -> more strong in close-ups and pls register my prompts ;)
face enhancer_v2 -> much more smother and better ;)
please merge in your checkpoint, and tell me, btw i have less trained loras
more hints below! ->
face enhancer
(learning: ran on an intel-i7 with an RTX4060, 7 hours with 300 images)
its a lora file, so copy in your lora folder and use it like usual
often it works without changing the face too much, i suggest weights 0.2 until 0.8, the higher the less background and it works more for closer faces!
sometimes minor improvements are possible through sampling steps 30 up to 60
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 ;)
in faceanhancer I tried to include many cultures, 11-if i remeber^^ with old and young content, at the moment only woman
Hints:
see my article:
https://civitai.com/articles/1890/better-faces-lora
https://civitai.com/articles/1826/sdxl-prompts
All SFW!
