Carmella Rose is an American model and social media personality, with around 2.5M followers on Instagram.
130-step TI trained on a dataset of 15 images with these settings.
Appreciate my work? My TIs are free, but you can always buy me a coffee. :)
Curious about my work process? I have summarized it here.
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 (c4rmr0se:0.99), a woman as a movie star, modelshoot style, (extremely detailed CG unity 8k wallpaper), photo of the most beautiful artwork in the world, professional majestic oil painting by Ed Blinkey, Atey Ghailan, Studio Ghibli, by Jeremy Mann, Greg Manchess, Antonio Moro, trending on ArtStation, trending on CGSociety, Intricate, High Detail, Sharp focus, dramatic, photorealistic painting art by midjourney and greg rutkowski, (white turtleneck top:1.2), ((movie premiere)), (long skirt), ((standing near a movie theater)), ((paparazzi in the background)), (looking at viewer:1.2), (detailed pupils:1.3), ((closeup portrait:1.1))"
Description
130-step TI trained on a dataset of 15 images with these settings.
FAQ
Comments (8)
What a beautiful girl 💯
Hey, I noticed that you're now doing 130-140 steps for your recent TIs, as opposed to the 900-1500 you were doing when you wrote out your methodology:
https://civitai.com/models/56570/renata-valliulina?commentId=118383&modal=commentThread
Have you changed anything else in your process that has made the sweet spot move that much?
Hey! Yes, my settings have changed, which explains why my TIs peak much earlier now. Instead of gradient 2, now my gradient equals the number of pictures in the dataset (usually 15). That means I'm running 3 full epochs per step (with my older settings I ran 1 epoch every 3 steps, so they took much longer in terms of steps to train).
@JernauGurgeh Gotcha, thanks! Yeah, I've been doing batch size 6 and gradient ~5 (however many multiplies out to the number of images — so 30 images = batch 6, gradient 5 — and that also seems to peak around the same time as yours.
@j1551 It's been a long time since I've trained with so many images, but that's a high batch size (and gradient), and you're running a full epoch per step, so I guess it makes sense that your TIs will train quite fast. Good luck with your training, mate!
Poor girl !
She should report this to the Police !
She has 2.5 Million people following her around and she can´t even get out of the house !
holaa would you consider katie mcgrath? she doesn't have her own good lora/embedding
I'll add her to my list! 🙂
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.