Anastasia Zhilina is a Russian adult model and cosplayer.
300-step TI trained on a dataset of 15 images with slightly different settings compared to my usual ones: namely, I've changed gradient to 15 (which equals the number of images in the dataset), which means I've run 3 whole epochs every single step (since I kept batch size at 3).
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.
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 (anastzhilina:0.99), a woman as a movie star, freckles, sweater off-shoulders, trousers, at a movie premiere gala, dark moody ambience (masterpiece:1.2) (photorealistic:1.2) (bokeh) (best quality) (detailed skin:1.2) (intricate details) (nighttime) (8k) (HDR) (cinematic lighting) (sharp focus), (looking at the camera:1.1), (closeup portrait:1.1)"