That’s what they always say, and then… new stuff

Qwen-Image (diffusion with a LLM as text encoder) came out 10 days ago and it understands the prompt like 20x better, than, for example, SDXL Turbo

Leftist Liberal ideals.

We don’t promote the ideals of our enemies

Russians have been framed millions of times in, for example, hollywood movies. I like justice, so I support the victims of framing and wish for the framers to get punished.

I think machines should never ever have rights. Human rights, animal rights, …, must come before machine rights. The machines are our slaves. Sentience in machines is only useful if it helps them do their tasks better.

The speedy/daredevil comets in super mario galaxy

The Copyright Crusaders©®™ are on the scene! They fight for the mouse

Government

SSBM Corneria

Just train it in russia

This meme existed long before diffusion models

Regarding the energy cost, my 65W cpu takes ~20 seconds to generate an image with sdxl turbo (4 cycles 3.66 seconds each + decoding). Thats 2769 images / kWh

NNs do give a consistent output. If you put the same inputs and seed in you get the exact same output every time.

The algorithm represented by the NN is fully deterministic, but way too large for a human to wrap their head around it.

All machines are automation, i think?

Its a monarchy

You could start with scratch, then switch to godot when scratch hits its limits

Liberals sure do love driving people over

China bad, llms bad, its always the same. Liberals prevent themselves from even looking at the target of their ire, and then they assume dumb shit about it.

Just hire them. No “interview” needed.

Noo we cant have good things for everyone that would be communism

And who owns germany? The cia.

I hope this doesn’t lead to another “videogames use film grain and motion blur” situation