Playing with emotion in a funny way
Playing with emotion in a funny way
If you’re asking whether I generated it, yes, I generated it with Dreamshaper v7.
parameters
portait of a young red head freckled woman (confused concerned upset questioning (funny fun amused (cringe (raised eyebrow) shy blush ashamed bruh face) emotional smile expression) emotion), (wearing a pearl necklace and hoop earings), (short hair bun princess), (vibrant neon purple eyes), (8k, 4k, HD, high definition, ultra quality, extreme detail, hyper realistic, UE5) lora:add_detail:1.2
Negative prompt: verybadimagenegative_v1.3, badhandv4
Steps: 60, Sampler: Euler a, CFG scale: 7, Seed: 78986836, Size: 768x768, Model hash: ed989d673d, Model: dreamshaper_7, Lora hashes: “add_detail: 7c6bad76eb54”, Version: v1.3.2
Upscaled version:
There is no reason to be upset. 😂
It definitely depends on the model. But if you want better results you’re going to want to use adetailer.
I threw your prompt into dreamshaper 6.31 (because it’s the latest version I had on my server). Here’s with no adetailer:
Here’s with adetailer but using the exact same prompt as the main image (leaving both fields blank but turning adetailer on):
Here’s with adetailer but putting only the expression part in the positive prompt. Negative prompt still the same as the main image.
(confused concerned upset questioning (funny fun amused (cringe (raised eyebrow) shy blush ashamed bruh face), <lora:add_detail:1.2>
Now, probably a good idea to have redhead woman in there or something, but my point is how rapidly you can improve things with very minimal effort. If you’re willing to mess around with adetailer prompts and denoising strength, you can do a lot with faces.
LOLOLOL thank you again!
Recently I released my embedding toolkit which has a variety of tools and fixers I've come up with over the past 6 months. I considered adding my e...