Kaley Cuoco is an American actress, mainly known for her role as Penny in The Big Bang Theory series.
Update: Retrained from scratch, applying my current settings. This version is step 140 of a TI trained on a dataset of 15 images.
Curious about my work process? I have summarized it here.
Do you have a specific idea for a TI in mind? Visit my website and let me know.
Building a good prompt with my TIs
You're obviously free to experiment, but bear in mind that my TIs are trained with a more or less fixed phrasing, that normally starts with:
"photo of EMBEDDING_NAME, a woman"
So I recommend always starting your prompt like that and then building the rest of the prompt from there. For instance, "photo of beautiful (kcu0c0:0.99), a woman with perfect short blonde hair, wearing Golden Yellow (cassock:1.1), (cosmic background:1.1), (closeup), modelshoot style, (extremely detailed CG unity 8k wallpaper), professional majestic photography, (Leica M6 Camera), 24mm, exposure blend, hdr, faded, extremely intricate, High (Detail:1.1), Sharp focus, dramatic, soft cinematic light, (looking at viewer), (detailed pupils), 4k textures, elegant, ((((cinematic look)))), soothing tones, insane details, hyperdetailed, low contrast".
Please also note that I'm using the "add detail" LoRA for my example pics. I recommend setting it around 0.5 for best results. CLIP Skip should always be set at 1 when generating pics with this TI.
Description
450-step TI trained on a dataset of 18 images with my new settings.
FAQ
Comments (6)
Cheers my bro. In the case of a small dataset, the disadvantage of full batch iteration killer is not very apparent, and it is still possible to complete enough iterations in a relatively short amount of time.
Yep, I have to say it looks really really good!
New process?!? Seems to work great!
The vector strength of the file you posted is only 0.592 for reference
A other beautiful embedding thank you Jernau! She turned out great!:)
there was another embedding here on civit which sadly got banned and it was wAAAAy better
Edit:
Works now, read this comment if you have issues with it not working ^^ thx again @JernauGurgeh 👍❤
Old comment:
Does not seem to work at all?
I just get a random woman, or if i really push the weight (to 2.0) i just get some sort of extremely random patchwork artwork thing of god knows what??? it could be a breakfast table or backyard or garbage dump, i genuinely have no idea what its trying to make 😂
Since it appears to work for others, anyone have any idea of what i could be doing wrong????? i'm so confused.
Tried this prompt:
"stunning 21yo (k4l3ycu0c0:0.99) in a bed, 1girl, blonde, messy bun, green eyes, masterpiece, detailed face, detailed skin, detailed eyes, 8K UHD, ultra wide angle, hyperrealism, hyper detailed"
With this negative prompt:
"3d, cartoon, anime, girl, loli, young, frame, blurry, drawing, sketch, ((ugly)), ((duplicate)), (morbid), ((mutilated)), (mutated), (deformed), (disfigured), (extra limbs), (malformed limbs), (missing arms), (missing legs), (extra arms), (extra legs), (fused fingers), (too many fingers), long neck, low quality, worst quality"
tried on a bunch of different models with the automatic111 webui thing, using --xformers (0.0.16rc425) and --medvram commandline args, plus these settings: 30 sampling steps, CFG 7, UniPC sampling method, Hires.fix (from 448x640 to 768x1024, with denoising 0.35)
Happens with all models i tried on (bscly 30+ well rated realistic ones from the past few months) tried redownloading several times too with no change either? color me confused af.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.