Georgina Mazzeo is a Venezuelan fashion model and social influencer with almost 5M followers on Instagram. For her TI, I used a dataset of 40 high quality images, which I trained for 4000 steps with the usual gradual learning rate. For now I've settled on the final step, which seems really accurate and, as far as I can tell, not too overcooked, as it is working very well with a number of different prompts in various models even without modifying the specific weight of the embedding. Hope you enjoy it!

Updated TI: Please check the "About this version" section for further info.

This is a 135-step TI trained on a dataset of 15 images with these settings.

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 (gmazze0:0.99), a woman with perfect hair upsweep updo, wearing (shoulder sash:1.1), (plain {yellow|black|red|blue|green} background:1.1), modelshoot style, (extremely detailed CG unity 8k wallpaper), professional majestic photography, ((smiling:1.2)), (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, soft cinematic light, adobe lightroom, photolab, 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.