Trained a new model for 'realistic photos' - whatever that ever means. It works pretty well.
Imagine where the quality will be in a year. #stablediffusion#portrait
Film Camera - few individual portraits
Film Camera 2
Film Camera 3
Sometimes they fail! Quite spectacularly, I might add.
And sometimes the failures are more subtle - me trying to include activities too hard into the image.
Portrait orientation sometimes exhibits this truly spectacular failure...
failure - more like secret success!
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Dreambooth training for Stable Diffusion is extremely powerful. You can train a new token to the "person" class to create very convincing looking images of them. I've posted some examples in the past days.
But it's not the coolest thing you can do...
You can train the "style" class to create new styles. For instance the "arcane" style is well known - it skews all results to this particular Riot games style.