Example prompt: "A woman's face. Whitish translucent cum is splattered across her face and chest."
Flexible prompting: see example images.
Note: "whitish, translucent cum is splattered..." keeps character likeness. If you dont care about likeness you can try things like "her face is covered in milk" or "milky cum" and you might get thicker goo.
Important descriptors: whitish, translucent, splattered
Other descriptors: gooey, stringy, thick, wet, milky
Settings:
LoRA strength: 1.0
Steps: 20 - 30
Goals:
Should not impact: ethnicity, age, style, image quality, camera angle etc
Small file size (quicker renders)
Decent goop
History:
V1 (first attempt): complete failure, deleted
V2: unrealistic
V3: better goop, but poor quality and too much training person likeness
V4 (after 17 attempts): better goop, still too much effect over age/ethnicity/likeness
V5 (after 90 attempts): least influence over subject, but goop can be a little crazy
V6 (hunders of attempts): slight influence over subject, but better goop than V5
⚠️ beta versions will be removed ⚠️
Description
FAQ
Comments (7)
what is the best way to make these work with character loras?
Same thing, it's working OK on its own but very very little along with a character lora. Too bad because looks promising
inpaint manually, like usual.
Did you had a V4 beta1 that you removed? It was working better for me , can you please reupload it? Thank you so much
i put it back. what do you prefer about it? i had problems with it
Thank you for putting it back, v4 ( and the others ) works for me on FLux Schnell but with FLux Dev the "fluid" looks like chalk, basically it is ignored. but for some reason v4beta1 works well, I am using it on a third party provider and speaking with some people over there it seems that most CIvitAI models are trained quintized and they run the full DEV unquintized model , have you trained beta1 differently ?
@sapo1974 v4-beta1 was a "rapid" training (single epoch), so maybe that's why? V4 was full training, selecting an specific epoch from many epochs. so yes, trained differently
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.