So the way I used to get consistent characters was using a mix of:
img2img (denoise: 0.7) with the same model posed into the position desired.
Then using a weighted down character lora and a weighted down celeb name, to help give a consistent base.
And finally a prompt with all the same details each time. (Well apart from changing expressions in the prompt each time.)
Wait. So the way to get consistent characters without LoRA training is to use a LoRA?
Does anyone have any themes they really like? I saw one from BitBrain that looks pretty good: https://github.com/bitbrain/godot-dash
Just finished playing Axiom Verge. Since I picked up a SteamDeck, I'm trying to play through my library. I'm trying to figure out which game in my library to tackle next between Blasphemous, Forager, or Spiritfarer.
I don't know. I read pretty often, and I learned how to do that at school.
I felt the same way when the videos of Russians torturing and killing POWs was going around.
You're just teaching the Ukrainians that they should always fight instead of getting captured.
I wish that game would come to Steam. I loved Ogre Battle as a kid.
My main issue with using the general chatbot is that it's an incredibly inefficient way to convey information. For writing tasks I essentially need to type most of the answer first to get reasonable outputs when considering my actual constraints.
More specialized tooling will have these constraints built-in, which will increase productivity.
Even if we have the perfect general chatbot, it's still a lot of work to concisely describe your requirements to it.
It's a computer vulnerability or exploit which has not been discovered before (or at least the software developer wasn't aware of it).
0-day comes from the number of days the software developers have been informed of the vulnerability. Normally security researchers will tell a company about an exploit and give them some time to fix it before telling the public.
I liked it, especially for how cheap it is. A lot of mechanics that are simple by themselves, but make complex strategy. Sure, sometimes your run falls apart because of a few bad rolls, but you'd expect that in a dice rolling game.
I had this exact same thinking culminating in me downloading Connect this morning. Also looking at Liftoff, since I'll have a better chance to contribute, but so far I'm enjoying that Connect works better and I can actually leave my local instance.
Thanks for sharing this article. I agree that those points mentioned are not possible for GenAI. It is a pipe dream that GenAI is capable of global governance, because it can't really understand the implications of what it means. It's a Clever Hans and just outputs what it thinks that you want to see.
I think that with GenAI there are some job classes that are in danger (tech support continues to shrink for common cases, etc.), but mostly the entry-level positions. Ultimately, someone who actually knows what's going on would need to intervene.
Similarly for things like writing or programming, GenAI can produce okay work, but it needs to be prompted by someone who can understand the bigger picture and check it's work. Writing becomes more editing in this case, and programming becomes more code review.
I agree. My 3070 runs the 8B Llama3 model in about 250ms, especially for short responses.