*** Its a Tool - LORA ! ***
...
higher CFG(10-15) images with a plus-lora are not so overexposed or have that cartoon style.
same meaning in the other way, low CFG(1-3) images mostly very real but also very boring, so with negativ-lora weight you can "pimp up" the moody.
...
in short words let me explain...
It seems that this is a kind of CFG slider (but more), for example
CFG ~ 2 -> loraweight:-0.5 (in this combiniation you get good images)
CFG ~ 12 -> loraweight: 0.5 (in this combiniation you get good images)
for DPM Sampler
...
for Euler_a it seems some kind of turbo
CFG~4
Steps ~10
loraweight: -0.4 to -0.8
maybe its useful for turbo/lcm models to have a smoother cfg/slider ?!?
for abstract art -> minus is more real, plus is more abstract/fantasy
for face portraits, lets say you have a prompt:
eg
"portrait photo of a 20yo messy blond haired woman. wears a offices suite."
cfg 2 - hair ist not that messy and borring surrounding
cgf 5 - hair is messy
cgf 12 - the hair are more messy, but somehow overexposed/cartoon
on cgf 2: you can use that lora with a weight arround -0.5 to get a more interesting image with very messy hair ;)
on cgf 12: you can use it with weight arround 0.5 to get mroe real images
.
dont blame me its a tool, maybe you can play with it and tell me more ;)
:*
Description
smaller, only a bit different
FAQ
Comments (4)
In case anyone still wonders what this does exactly...
At negative weight (for low cfg):
* higher contrast
* better colors
* sharper image (equivalent of "high-res")
* adds details (less pronounced than a real detailer but it's there)
If you don't have access to plugins, for example when using the civitai generator, it's a pretty nice tool.
I love it. Its great to turn down the contrast and add a soft touch to pictures. Well done lora - try it.
This really needs to be talked about more. IDK what kinda magic was used in the training of this but it just works. Honestly give it a try and see for yourself.
When used in the negative it fixes my issues with Pony at low CFG and when using distilled/accelerators.
At low CFG, slap on this lora at negative values like -0.5 to -1.0) and it helps with:
prompt adherence
cohesive image
prevents image collapse
improved backgrounds
THX, it was a try and it works in some cases ;)
i dont remember, maybe it was an lora-extraction from a turbo model ???
the distilled Lora for FLUX i have extracted from the model
https://civitai.com/models/977247/flux-distilled-lora