Synthetic Media & Generative AI News and Discussions

[wjfox]

This has been mentioned elsewhere on the forum, but here's a more indepth look at it.

I'm gonna be using this myself, for some futurology videos.

[funkervogt]

I like how this article highlights how humans unconsciously keep raising the bar for what counts as "intelligence."

When I showed my friends the sonnet by ChatGPT, they called it “soulless and barren.” Despite following all the rules for sonnets, the poem is cliche and predictable. But is the average sonnet by a human any better? Turing imagined asking a computer for poetry to see if it could think like a person. If we now expect computers to write not just poems but good poems, then we have set a much higher bar.

https://www.washingtonpost.com/books/20 ... in-poetry/

Also, I wonder if the author made the mistake of telling his friends that a machine wrote the sonnet before he asked them to critique it. Of course such knowledge about its authorship would have biased them.

[Yuli Ban]

[wjfox]

[Ken_J]

do not like. it's too much like those youtube videos of the eyes and mouth on pieces of fruit. Doesn't look even remotely natural.

[ººº]

do not like. it's too much like those youtube videos of the eyes and mouth on pieces of fruit. Doesn't look even remotely natural.

It reminds me of those channels with semi-3d anime characters but way more rigid.

[Ken_J]

It reminds me of those channels with semi-3d anime characters but way more rigid.

like v-tubers? yeah those are usually done through a limited motion capture feature, sometimes through expensive rigs, sometimes through web cam software. but this looks more like a simple set of stationary images of a non-talking model, with talking animations swapped over the facial features. there are some better experiments out there right now.

youtube.com/watch?v=3wQBsFftbv8&list=PLLM1VrmGfDzLt_1vsrHhAoQwAtyymWkHy&index=42

[wjfox]

[wjfox]

youtube.com/watch?v=3wQBsFftbv8&list=PLLM1VrmGfDzLt_1vsrHhAoQwAtyymWkHy&index=42

Just a tip. You need to delete everything from &list onwards. And include https:// at start of URL.

[Ken_J]

youtube.com/watch?v=3wQBsFftbv8&list=PLLM1VrmGfDzLt_1vsrHhAoQwAtyymWkHy&index=42

Just a tip. You need to delete everything from &list onwards. And include https:// at start of URL.

previous to the edit it included the https: // at the start. but it also showed up as unavailable for some reason in a big box. I just trimmed it so that it didn't eat up half a post with a broken player, figuring people could copy the link if they wanted to follow it.

[Cyber_Rebel]

The future of online avatars. That tutorial was also surprisingly simple, and it's not too difficult to imagine a service not too long down the line which combines all these A.I. tools into a single avatar generating interface. The fact that it still somewhat looks a little robotic is irrelevant considering how much this technology will improve, likely in a very short timeframe. Imagine chatbots having their own A.I. animated avatars as well, which is likely already in development. If Character.AI someday implements this, it's basically over.

Despite a very rough start, this decade is looking more and more promising by the day.

[Yuli Ban]

[spryfusion]

https://research.runwayml.com/gen2

[wjfox]

Adobe made an AI image generator — and says it didn’t steal artists’ work to do it

Mar 21, 2023, 1:00 PM GMT

Adobe is finally launching its own AI image generator. The company is announcing a “family of creative generative AI models” today called Adobe Firefly and releasing the first two tools that take advantage of them. One of the tools works like DALL-E or Midjourney, allowing users to type in a prompt and have an image created in return. The other generates stylized text, kind of like an AI-powered WordArt.

This is a big launch for Adobe. The company sits at the center of the creative app ecosystem, and over much of the past year, it’s stayed on the sidelines while newcomers to the creative space began to offer powerful tools for creating images, videos, and sound for next to nothing. At launch, Adobe is calling Firefly a beta, and it’ll only be available through a website. But eventually, Adobe plans to tightly integrate generative AI tools with its suite of creative apps, like Photoshop, Illustrator, and Premiere.

“We’re not afraid of change, and we’re embracing this change,” says Alexandru Costin, VP of generative AI and Sensei at Adobe. “We’re bringing these capabilities right into [our] products so [customers] don’t need to know if it’s generative or not.”

https://www.theverge.com/2023/3/21/2364 ... -announced

[wjfox]

Credit: David Foster on LinkedIn

[wjfox]

[Yuli Ban]

Another one of those things I called, from way back in 2017: synthetic media was always going to reach photorealism before hand-crafted CGI.
CGI might never actually truly approach photorealism because of the time and effort necessary, whereas generative AI is essentially a cheat code to do it with a trillionth of the effort.

It remains to be seen how soon someone manages to cross generative AI with video games to create the first truly photo-real graphics.

[Cyber_Rebel]

[wjfox]

[Yuli Ban]