Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Are C3.ai’s High-Profile Partners Enough to Offset Missteps?

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights – Takara TLDR

OpenAI Gives Us a Glimpse of How It Monitors for Misuse on ChatGPT

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Video Generation

OpenAI’s Sora 2 is now available – these are the six craziest videos the internet has made so far

By Advanced AI EditorOctober 6, 2025No Comments5 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


It’s been a long time since OpenAI launched its original Sora model, creating one of the first AI video generators on the market. Since then the competition has come in thick and fast, knocking OpenAI off its pedestal.

OpenAI has come back with a vengeance, launching Sora 2. Not only is it better, faster and utilizes a better understanding of physics, but it even lets you create real people and utilize themes from TV shows and films.

That has been a controversial choice, allowing for deepfakes and permitting users to generate lots of videos of OpenAI CEO Sam Altman. However, in a crowded market it also helps OpenAI to stand out.


You may like

We’ve been testing it ourselves and will soon fill you in on our own experiences with the tool, but we’ve also been seeing what the internet has been up to and it’s a trip.

To show you what I mean, here are our favorite videos generated using Soma 2 so far.

Fail videos

Sora 2 Fail CompilationPrompt : A series of raw, grainy CCTV clips stitched together like a fail compilation. Each feed has a timestamp flickering in the corner, wide fisheye distortion, and washed-out colors. In one scene, a man carrying a stack of boxes in a convenience… pic.twitter.com/v4Un9LtmLKOctober 2, 2025

Video produced by D_studioproject

Sure, in theory a group of blurry videos of people falling over isn’t that impressive. And yet, it kind of is.

Get instant access to breaking news, the hottest reviews, great deals and helpful tips.

Here, Sora is able to recreate videos with motion and a lot of movement, while also achieving a blurred video effect that would be seen in low cost cameras.

If you look closely, it is still clearly AI. Objects blur in the background or the clock timings don’t quite add up. But compared to the AI video generations Sora was making before, this is a massive jump.

Modelling career

Sora 2 is mind-blowing.You can upload image references and have cameos interact with them.It generates a fully edited video complete with music, sound and lip sync, all from just ONE prompt. pic.twitter.com/zIKaeGg5gqSeptember 30, 2025

Video produced by Halim Alrasihi


You may like

This is one of the more… appropriate videos that has used Sam Altman in Sora 2. It also displays an interesting concept that I’ve not personally seen done in AI video generations yet.

By giving the generator both an outfit and a person, you can see how that outfit might look on them.

While a lot of Sora 2 generations seem to be leaning towards comedy or simply being very unhinged, this shows the practical capabilities it could have in the future.

Alien Masterchef

Chef critiques alien food on MasterChef, Sora 2 pic.twitter.com/zdAWk3tJyESeptember 30, 2025

Video produced by user Skirano

Where the above prompt shows how useful Sora 2 could be, this one shows the complete opposite end of a spectrum. Who knew we needed an alien version of Masterchef on our TVs.

This is also a great example of how well the AI sound generation works alongside the video. Is it slightly insane? Of course. But is it brilliant? Obviously.

“The foam tastes like battery acid” in that aggressive celebrity chef voice and a gentle tear falling at the same time is an Oscar worthy performance.

Car adverts

Sora 2 + Reference image + prompts.I uploaded my car images then added a base prompt that’s something like this:“use this car as a reference and make a cinematic automotive ad for this”or even simpler like “make automotive ad for this car” and then add some extra details… pic.twitter.com/A9tjILXtmTOctober 2, 2025

Video produced by AllarHaltsonen

Who says you need to spend hundreds of thousands of dollars on a car advert? This Sora 2 video creates a new version of the Lamborghini Urus, complete with a Nike collaboration.

The car looks realistic, it is driving according to the laws of physics (which is fairly new to AI video) and the voiceover fits the style that we all know and love from the many car adverts on TV.

Dog skydiving

Dog parachuting, GoPro footage, Sora 2 pic.twitter.com/c8kiEX6i4NOctober 1, 2025

Video produced by Skirano

It’s a dog skydiving… what more do you want? This video especially appealed to me, having spend a long time trying to get the original Sora model to create someone skydiving.

It was a complete mess, with limbs flying everywhere, facing morphing in and out and parachutes disappearing mid-fall.

Here, everything makes more sense. The dogs ears flap in the wind, the person is falling in the way we see skydivers fall, and you even see the parachute open at the same time as the man announces it.

While a more realistic sound for this video would just be an unbearable amount of noise and muffled voices, it is surprisingly accurtate in audio.

Movie quality clips

SORA 2 CAN BE PRETTY AWESOME!The camera shadows a weathered survivor’s piercing eyes in the midst of a sandstorm-swept ambush on rusted highways. Her skin is scarred by radiation and wrapped in scavenged hazmat rags, her gray eyes sharp with wary resolve. She layers patched… pic.twitter.com/DaUdoYP7TGOctober 1, 2025

Video generated by BrentLynch

While some are using Sora to create videos of dogs skydiving and blurry fail videos, others are making blockbuster movie clips.

This feels like something pulled straight from Mad Max or any other dystopian movie. While there are still hallucinations, most notably in the stickers on the car changing, it otherwise looks incredible.

The facial features and the way the hair moves feels incredibly natural. There is a lot going on in the background, which is something that would normally immediately cause issues for a video generator, but here it all works fine.

Like the other clips, the audio generated fits the theme and sounds quite impressive.

More from Tom’s Guide

Arrow

Back to Laptops

SORT BYPrice (low to high)Price (high to low)Product Name (A to Z)Product Name (Z to A)Retailer name (A to Z)Retailer name (Z to A)Arrow

Show more





Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleKyndryl Holdings: Navigating Growth Challenges and Transition from IBM with a Focus on Cash Flow and AI Opportunities
Next Article What Amazon shippers should prioritize this peak season
Advanced AI Editor
  • Website

Related Posts

MPA Demands OpenAI Fix Sora 2 Copyright System Amid AI Video Infringements

October 7, 2025

MrBeast Warns AI Videos Could Threaten Millions of Creators’ Jobs

October 6, 2025

What’s new in the AI video generator

October 6, 2025

Comments are closed.

Latest Posts

Basquiat Work on Paper Headline’s Phillips’ Frieze Week Sales

Charges Against Isaac Wright ‘to Be Dropped’ After His Arrest by NYPD

What the Los Angeles Wildfires Taught the Art Insurance Industry

Musée d’Orsay Puts Manet on (Mock) Trial for Obscenity

Latest Posts

Are C3.ai’s High-Profile Partners Enough to Offset Missteps?

October 7, 2025

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights – Takara TLDR

October 7, 2025

OpenAI Gives Us a Glimpse of How It Monitors for Misuse on ChatGPT

October 7, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Are C3.ai’s High-Profile Partners Enough to Offset Missteps?
  • Hybrid Architectures for Language Models: Systematic Analysis and Design Insights – Takara TLDR
  • OpenAI Gives Us a Glimpse of How It Monitors for Misuse on ChatGPT
  • IBM integrates Anthropic Claude into AI IDE and other tools
  • Microsoft retires AutoGen and debuts Agent Framework to unify and govern enterprise AI agents

Recent Comments

  1. Thomasdog on AI Learns Facial Animation in VR
  2. lukamodric on Nvidia to Launch Downgraded H20 AI Chip in China after US Export Curbs – Space/Science news
  3. Samepicl7Nalay on MIT’s Xstrings facilitates 3D printing parts with embedded actuation | VoxelMatters
  4. Thomashem on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. Lindseyror on Gemma 3N: Google’s Latest On Device Mobile AI Model

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.