I think it was post-processed to get it to snap to the grid. The model page includes an explanation that I don’t really understand. The gallery at the bottom also has a lot more interesting images.

Yeah, I was pretty confused when I looked at the prompt while writing the description.

I didn’t look too hard at the eyes when I found this one. I was taken by the layout and how close it looked to the source.

Record them anyway. There’ll be more ways to de-anonymize them in the future.

I can still hear that laugh.

That really does look nice.

This is definitely the type that grants wishes.

I wish I had the hardware for gens this good.

It’s just gibberish. I wrote the image description, the actual prompt is under the “full generation parameters” spoiler.

But the people making money off of all of that are mad now, hence this article.

It’s doing extra work and allowing other people to dictate how we use our space, for people that are going to break the rules anyway.

!lemmydirectory@lemmy.dbzer0.com has been running on this philosophy for ten months now. The sidebar even says:

Our community has bots making regular posts showcasing best content from communities in given categories to help promote them. Each category is assigned to it’s own bot to allow users blocking posts from unwanted categories and tailor the feed for their preferences without the need to block the whole community. Here’s the current list of bot accounts:

Yet look at all of Best_of_ai_bot’s posts. Immediately and heavily downvoted every time. The people doing this won’t care, and use the tags to target content.

I finally watched this show and thought it was pretty good.

It’s been going on for a while now on !lemmydirectory@lemmy.dbzer0.com. The sidebar even says:

Our community has bots making regular posts showcasing best content from communities in given categories to help promote them. Each category is assigned to it’s own bot to allow users blocking posts from unwanted categories and tailor the feed for their preferences without the need to block the whole community. Here’s the current list of bot accounts:

I’m not sure how much clearly marked posts are going to help the problem. I feel like the people browsing through all are targeting the content and won’t ever see the sidebar.

Yeah, detail usually breaks down on small stuff, but the whole hem is pretty messed up here.

You can’t be sued over or copyright styles. Studio Ponoc is made up of ex-Ghibli staff, and they have been releasing moves for a while. Stop spreading misinformation.

https://www.imdb.com/title/tt16369708/

https://www.imdb.com/title/tt15054592/

https://www.imdb.com/title/tt8223844/

https://www.imdb.com/title/tt6336356/

The dream is dead.

This doesn’t mean you can misrepresent facts like this though. The line I quoted is misinformation, and you don’t know what you’re talking about. I’m not trying to sound so aggressive, but it’s the only way I can phrase it.

Generating an AI voice to speak the lines increases that energy cost exponentially.

TTS models are tiny in comparison to LLMs. How does this track? The biggest I could find was Orpheus-TTS that comes in 3B/1B/400M/150M parameter sizes. And they are not using a 600 billion parameter LLM to generate the text for Vader’s responses, that is likely way too big. After generating the text, speech isn’t even a drop in the bucket.

You need to include parameter counts in your calculations. A lot of these assumptions are so wrong it borders on misinformation.

This is what Gible looks like, and unfortunately, it’s old enough to vote.

That’s my fault. I obviously don’t know the difference between a bison and a buffalo, and I wrote the title and image description.