I don't know if this community is intened for posts like this, if not, I'm sorry and I'll delete this post ASAP....
So, I play TTRPG (mostly online) and I'm a big fan of visual aids, so I wanted to create some chahrcter images for my charakter in the new campaign I'm playing in. I don't need perfect consistency as humans usually change a little over time and I only needed the character to be recognizable on a couple of images that are usually viewed on their own and not side by side, so nothing like the consistency you'd need for a comic book or something similar. So I decided to create a Textual Inversion following this tutorial and it worked way better than expected. After less than 6 epochs I had a consistency that was enough for my usecase and it didn't start to overfit when I stopped the training around epoch 50.
![Generater image of the character cosplaying as Amos from the Expanse](https://beehaw.org/pictrs/image/ec1d3bee-0326-4a73-a111-af3b7c91e3e7.png)
Then my SO, who's playing in the same campaign asked me to do the same for their character. So we went through the motions and created and filtered the images. A first training attempt had the TI starting to overfit halfway through the second epoch, so I lowered the learning rate by factor five and started another round. This time the TI started overfitting somewhere around epoch 8 without reaching consistency before. The generated images alternate between a couple of similar yet distinguishable faces.
To my eye the training images seem to have a simliar or higher quality than the images I used in the first set.
Was I just lucky with my first TI and unlucky with the other two and simply should keep on trying or is there something I should change (like the learningrate that still seems high to me with 0.0002 judging from other machine learning topics)?
I was at a small roleplaying convention last week. It was great to meet the others again after about a year and game with them. Unfortunately someone was rather generous with their flu viruses and I got my personal helping. So I'm on sick leave for the second say but luckily, according to the test it's just a flu and not the big bad C. On Monday I clobbered together a small template for my sister to build fake computer screens as props for TV shows... All in all a mixed bag of some good stuff and some annoying things...