https://civitai.com/models/328431?modelVersionId=573321
So what is good about this update
I have started training my LoRA at 1280x1280 instead of 1024x1024, this means higher res and easier details like hair clip and outfit
I had the old lora having flip augments on, this mirror'd her details sometimes and was just bad
other setting improvements
Get genning!
most subtle dramatard
Jump in the discussion.
No email address required.
Jump in the discussion.
No email address required.
eh I didn't set that
Jump in the discussion.
No email address required.
More options
Context
More options
Context
Accurate for a cat girl!
Jump in the discussion.
No email address required.
More options
Context
The overalls sticking to the booba looks weird ngl
Jump in the discussion.
No email address required.
Yeah the fabric that's simultaneously wrinkled and vacuum sealed to her skin looks weird in these. Tbf this is based on the training data of coomer artists so you can't entirely pin it on AI.
I've seen really good AI art (including from OP) but I think the excessive detail clashes with the anime art style. Too many fine lines, too much shading, way too shiny (why are the overalls shiny?).
Jump in the discussion.
No email address required.
More options
Context
More options
Context
Would
Jump in the discussion.
No email address required.
More options
Context
Jump in the discussion.
No email address required.
More options
Context
Give her a dumptruck butt that's bigger than her torso.
Jump in the discussion.
No email address required.
More options
Context
built for Big Human Peepee
Jump in the discussion.
No email address required.
Factcheck: This claim is both true and false.
Jump in the discussion.
No email address required.
More options
Context
More options
Context
AI. Still would though.
Jump in the discussion.
No email address required.
Jump in the discussion.
No email address required.
It was on the home page and I didn't bother to look at the hole, just saw cute cat girl.
Jump in the discussion.
No email address required.
Shut the frick up r-slur
Jump in the discussion.
No email address required.
Who are you, and why are you so dumb?
Jump in the discussion.
No email address required.
More options
Context
More options
Context
zoz
Jump in the discussion.
No email address required.
zle
Jump in the discussion.
No email address required.
zozzle
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
More options
Context
More options
Context
More options
Context
can someone make her do the sexo
Jump in the discussion.
No email address required.
More options
Context
Oh nice.
Do you think you could do like a beach/bikini one or is her outfit more or less baked into the lora?
Jump in the discussion.
No email address required.
it will probably work with a bit of tweaking, you might need to do things like put overalls into the negatives
Jump in the discussion.
No email address required.
That's likely a sign you've under tagged or over trained.
Jump in the discussion.
No email address required.
the model has so few images it's pretty much always going to be over trained , doing fewer than 2k steps also leads to garbage
Jump in the discussion.
No email address required.
Are you using synthetic data yet? That's the 6 month old fad for AI. Generate results, tag them good or bad and resubmit. Like a manual GAN.
Jump in the discussion.
No email address required.
I have long been using gens as data sets because there is only like 2 hand drawn images of her lol.
I just use my better cleaned up images
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
More options
Context
More options
Context
More options
Context
We serve food here sir
Snapshots:
https://civitai.com/models/328431?modelVersionId=573321:
ghostarchive.org
archive.org
archive.ph (click to archive)
Jump in the discussion.
No email address required.
More options
Context