Natalie Lee, better known as NataLee, Instagram model and influencer.
I thought it was about time I gave my very first embedding a paint-job. When I created it, I thought it was a poor attempt because I didn't really know how TIs worked and I was building pretty poor prompts. In retrospect, I now think it was at least a very decent TI, and I'm not really sure this new version improves upon it. I'll let you judge.
The new version is an 1800-step TI. I removed 5 pics from the original dataset of 23 to leave it at 18, and applied my usual settings.
Curious about my work process? I have summarized it here.
Appreciate my work? My TIs are free, but you can always buy me a coffee. :)
My very first embedding. It had a tendency to depict NataLee as a brunette, but other than that I think it was a pretty good TI. I probably got kind of lucky, as I didn't really know most of what I was doing at the time. xD
According to the automatically generated log, these were the settings I used:
"num_of_dataset_images": 23,
"num_vectors_per_token": 5,
"embedding_name": "n4t4lee",
"learn_rate": "0.004",
"batch_size": 3,
"training_width": 512,
"training_height": 512,
"steps": 1500,
Unfortunately I don't know what gradient I used. I suspect it was gradient 1, but I'm not 100% sure about it.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.