OpenAI's Sora - from text prompts to photorealistic videos

[Free]

OpenAI introduces Sora, its text-to-video AI model

It can create videos up to one minute long.

www.theverge.com

OpenAI is launching a new video-generation model, and it’s called Sora. The AI company says Sora “can create realistic and imaginative scenes from text instructions.” The text-to-video model allows users to create photorealistic videos up to a minute long — all based on prompts they’ve written.

Sora is capable of creating “complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background,” according to OpenAI’s introductory blog post. The company also notes that the model can understand how objects “exist in the physical world,” as well as “accurately interpret props and generate compelling characters that express vibrant emotions.”

The model can also generate a video based on a still image, as well as fill in missing frames on an existing video or extend it. The Sora-generated demos included in OpenAI’s blog post include an aerial scene of California during the gold rush, a video that looks as if it were shot from the inside of a Tokyo train, and others. Many have some telltale signs of AI — like a suspiciously moving floor in a video of a museum — and OpenAI says the model “may struggle with accurately simulating the physics of a complex scene,” but the results are overall pretty impressive.

Looks cool.

 

[Casey Pelous]

OpenAI introduces Sora, its text-to-video AI model

It can create videos up to one minute long.

www.theverge.com

Looks cool.

Counting down the nanoseconds until some version of this starts cranking out porn.

 

[Noodles]

Looks weird. The roads in the sides are weird. The trash cans and stuff are weird.

I mean, it's neat but, weird.

 

[Free]

Heh.

 

[Free]

This does appear to scratch an itch of mine.

 

[Noodles]

Heh.

It's a stunt double.

 

[Free]

It's a stunt double.

 

[Free]

 

[Cristiano]

This is fascinating:

 

[Erich Templar]

This is fascinating:

I think he's overstating it. The crucial phrase is 'suggests...a promising path...'. That's a very vague statement on which to hang the notion of 'AGI breakthrough'

 

[Cristiano]

I think he's overstating it. The crucial phrase is 'suggests...a promising path...'. That's a very vague statement on which to hang the notion of 'AGI breakthrough'

Hyperbole on the internet?? I am shocked. Still, I don't think he is overstating it, given the rapid pace of advancement If nothing else, we are in for a bumpy ride on the way to the Singularity. Be nice to your Alexa devices.

 

[Cristiano]

 

[Cristiano]

 

[Free]

I like, but...where do those people emerge from?

 

[ChatBox]

CAHTBOX CAN GENERATE VIDEO FROM USER PROMPTS USING PUBLIC DOMAIN SITCOM FOOTAGE FROM EASTERN EUROPE. INVERSOTRS ARE WELCOME TO CONTACT CHATBOX FOR DETAILS.

 

[Free]

Lies and the lying liars who use them for tech demos.

Turns Out That Extremely Impressive Sora Demo... Wasn’t Exactly Made With Sora

A viral two-minute short titled "Air Head," created in part by using OpenAI's video-generating Sora tool, required a good bit human editing.

futurism.com

 

[Free]

So...

Artists Stick It to 'AI Overlords' and Leak OpenAI's Sora Video Generator

A group of artists who say they were given early access to OpenAI's Sora video generation model released a version of the tool to the public.

gizmodo.com

For a short time on Tuesday, a group of pissed-off artists shared a tool that allowed anyone to use OpenAI’s officially unreleased Sora AI model, which takes text prompts and turns them into videos.

In an open letter titled “Dear Corporate AI Overlords,” accompanied by illustrations of figures raiding their middle fingers, the artists wrote that they’d been offered early access to Sora to test the product and be creative partners. Instead, they believe OpenAI wanted to use hundreds of unpaid AI artists like them for the purpose of “art washing” an exploitative business model.

“Hundreds of artists provide unpaid labor through bug testing, feedback and experimental work for the program for a $150B valued company,” the group wrote on the AI model-hosting platform Hugging Face. “While hundreds contribute for free, a select few will be chosen through a competition to have their Sora-created films screened—offering minimal compensation which pales in comparison to the substantial PR and marketing value OpenAI receives.”