People (who knew about it) were generally excited I think before they released the teaser
I'm pretty sure they announced they were making the movie like 3-4 years ago or something
next up: microsoft announces development of Bethesda's next game will be largely outsourced
Just read the wikipedia list of common misconceptions
Chromebooks are insanely locked down at schools. I got one on eBay for $40, installed linux, and now it can play Minecraft Java at 60 fps so that’s something.
This is at JFK, does anyone know what they are used for? There wasn’t an obvious time when it was taking a picture.
They can't. AI has hallucinations. Google has shown that AI can't even rely on external sources, either.
Prompt: A cyberpunk scifi painting of a floating city in the air above the sea
It uses a new, fancier, 18GB text encoder (t5) to follow the prompt much more closely. It isn't perfect, but its much better than SDXL in my opinion. It does seem to be a bit worse at photorealistic subjects and has a tendency to create 1-pixel vertical lines.
Some other images:
impressionist, a woman sits in the middle of a crowded cyberpunk street, people bustling around, orange and blue glowing signs, warm atmosphere
a bright cinematic photo of a solarpunk city at midday, skyscrapers, steel, glass, vines and fields of vivid tropical plants
"you now have to spend more money to survive" -> "people are now spending more money" -> "the GDP is going up" -> "the economy is doing well!"
not really a joke article because the guy did make it, but it also isn't a product, it was just an 'art project' by the guy
I agree with the chef.
I get around 1 image every quarter of a second on my 3060. The quality isn't up to par with regular SDXL (not even close) but it follows prompts well and is extremely fast. Here are some of the best images in this batch:
Prompt: "impressionist oil painting, watercolor, a crying old southern man eats cheese at sunset in front of a futuristic dystopian cyberpunk city"
Material:
3D model:
Original image:
"Solved it" for a game just means "approximated it well enough that the average user won't notice".
They massively changed the UI in 2019, in version 2.8. Hasn't changed much since then though.
If you remember Blender having a bad-looking light grey UI and no support for multiple workspaces, that's the old version.
The actual CGI looked fine, its just the art style and general vibe that was bad IMO
you could tell from watching the trailer that its probably going to be a ton of cringey stuff mostly aimed at 8 year olds