I'd tag it as "wearing a suit, flowers in background" or "wearing a suit in front of flowers". Basically what you're doing with the description is saying "I'm going to show you an image of this_awesome_person, please ignore that they're wearing a suit, flowers in background". If you also describe that it's a man, you ask SD to ignore the fact for the training.
P.S.: Please ignore the different accounts, I got confused, made two, this one's the main one...
same here... just right now downloading the font, thinking if I don't at least give it a try, I'll forever wonder what it'd be like...
Creating somewhat consistent Characters as Illustrations for TTRPG
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.
!Generated image of a character wearing a black hoodie standing in a rundown neighborhood at night !Generated image of the character wearing a black hoodie standing on a street !Gerneated image of the character cosplaying as Ironman !Generater image of the character cosplaying as Amos from the Expanse
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)?
An open minded crowd that creates an "us" without the band even beeing on stage yet and a band that knows how to and is willing to tap into that feeling and just kind of joins the crowd. As opposed to a crowd that separates into small groups where everyone eyes the others to find out who's the best or most hardcore fans or a band that's tired because it's the end of a long tour and would rather chill at home than play that gig.
Since it doesn't seemed to be mentioned by anyone (or I missed it), I'm going to say Robo-Rally... Programming your robot through a racetrack on a moving factory floor using drawn command cards, bumping into others, knocking the off course and ending in a totally wrong spot yourself because you miscalculated a step...
I'm currently running a campaign in D&D5e and am playing in two others, there's a Scion campaign that I play in and yesterday a short campaign for Vampire the Masquerade had it's kick off. Additionally I'm currently planning a few shot for TORG Eternity that I'm going to run during summer break with the Scion group.