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

Smuggled Nvidia AI Chips Worth $1 Billion Flood Chinese Black Market Despite U.S. Export Controls

Claude Code AI Automations for Community Management in 2025

Earnings Shock: Why IBM, Chipotle, and American Airlines Tumbled—and What Comes Next

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
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Video Generation

Google Is Rolling Out More Ways to Turn Photos Into Videos With AI

By Advanced AI EditorJuly 24, 2025No Comments4 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


The big conversation surrounding AI video generation is, of course, deepfakes and misinformation. Google’s Veo 3 model can produce hyper-realistic videos that might trick many of us into thinking they’re real, which poses a serious risk. Are you sure that video you just watched was actually recorded by somebody? Or was it produced entirely in a computer from a simple prompt?

Not all AI-generated video outputs are this sophisticated, however. Some seem geared more towards simple novelty, like Google’s photo-to-video converters. The company first rolled out such a tool to paid subscribers back in April. Powered by Veo 2, the tool animated still images based on your prompts, turning pictures into short 720p videos of up to eight seconds in length. Unlike the viral videos created using the company’s most recent model, Veo 3, these videos seem more like a party trick—an artificial Live Photo, if you will.

Photo-to-video is rolling out to two new apps

Google has been working on bringing the feature to more apps, and, as a result, more users. This month, photo to video capabilities landed for paid users using Gemini, this time powered by Veo 3. (Despite the more advanced model, these videos are still short and 720p.) Perhaps the biggest change here is that you can add audio to these videos, which helps sell the effect. Now, per the The Verge, the feature is heading to two Google products, without needing to pay for them: Google Photos, and YouTube Shorts.

These new features are once again powered by Veo 2, so you’re getting the previous-generation video model here. (Veo 3 is apparently coming to YouTube Shorts later this summer.) In addition, you can’t add custom prompts to the tool. Instead, you can choose from preselected prompts, or choose the “I’m feeling lucky” option. That might mean the photo of a crosswalk light turns into a video of the walk sign dancing. (This is a real example from Google, by the way.)

The feature in Google Photos will generate videos up to six seconds in length, but YouTube Shorts lets you decide how long you want the video to be. If you’re not happy with the generation, you can choose to try again, or hit the thumbs down icon, which helps train the model. (There’s also a thumbs up icon here as well.)

Like all AI-generated results, Google’s photo-to-video tool warns that it is experimental, and that “results may be unexpected.” That likely is cover for Google, so that if your animations do anything offensive or disturbing, it’s not the company’s fault. It’s AI: What are you going to do? To that point, there shouldn’t be any confusion as to whether these video outputs were created with AI, as Google says each will generate with a visible label to denote its artificial origin. Videos will also include an invisible SynthID watermark, which Google bakes into all of its AI-generated products to help users identify real content from AI content.

The new tools are currently available in Google Photos in the U.S. for iOS and Android, and will be rolling out over the next week to YouTube Shorts in the U.S., Canada, Australia, and New Zealand.


What do you think so far?

Who are these features for?

I admit, I don’t use many (or any) AI tools in my life, so perhaps I’m not the best person to judge the merits of something like this. But I do wonder: Who is this for?

I can imagine photo-to-video tools being interesting for a generation or two. Look! I animated this image of the family dog. And now, the doodle I drew this morning is moving! And now, I’m bored.

There’s a novelty to these tools, but, in my opinion, it wears out fast. While it might be fun to share these AI videos with friends from time to time, I’d much rather look at a real photo than a fake animation derived from that photo. When you try to make the case for this feature beyond novelty, it falls apart for me. Google uses an example of a photo of a man smiling: Veo 2 animates the man throwing leaves in the air. That animation not only has nothing to do with what’s going on with the image in the first place, it’s just a false memory—something that never actually happened. Give me the still version of something that did happen any day.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleOpenAI prepares to launch GPT-5 in August
Next Article Nvidia AI chips worth US$1 billion entered China despite US curbs: FT
Advanced AI Editor
  • Website

Related Posts

Midjourney brings AI video generation to Discord, and now you can make them loop seamlessly

July 25, 2025

YouTube Shorts & Google Photos Are Getting Great New Gen AI Video Tools

July 24, 2025

YouTube Shorts gets a new AI photo-to-video feature, alongside more AI effects and creation tools

July 24, 2025

Comments are closed.

Latest Posts

Auction House Will Sell Egyptian Artifact Despite Concern From Experts

Anish Kapoor Lists New York Apartment for $17.75 M.

Artist Loses Final Appeal in Case of Apologising for ‘Fishrot Scandal’

US Appeals Court Overturns $8.8 M. Trademark Judgement For Yuga Labs

Latest Posts

Smuggled Nvidia AI Chips Worth $1 Billion Flood Chinese Black Market Despite U.S. Export Controls

July 25, 2025

Claude Code AI Automations for Community Management in 2025

July 25, 2025

Earnings Shock: Why IBM, Chipotle, and American Airlines Tumbled—and What Comes Next

July 25, 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

  • Smuggled Nvidia AI Chips Worth $1 Billion Flood Chinese Black Market Despite U.S. Export Controls
  • Claude Code AI Automations for Community Management in 2025
  • Earnings Shock: Why IBM, Chipotle, and American Airlines Tumbled—and What Comes Next
  • CoSyn: The open-source tool that’s making GPT-4V-level vision AI accessible to everyone
  • Meta names Shengjia Zhao as chief scientist of AI superintelligence unit

Recent Comments

  1. Janine Bethel on OpenAI research reveals that simply teaching AI a little ‘misinformation’ can turn it into an entirely unethical ‘out-of-the-way AI’
  2. 打开Binance账户 on Tanka CEO Kisson Lin to talk AI-native startups at Sessions: AI
  3. Sign up to get 100 USDT on The Do LaB On Capturing Lightning In A Bottle
  4. binance Anmeldebonus on David Patterson: Computer Architecture and Data Storage | Lex Fridman Podcast #104
  5. nude on Brain-to-voice neuroprosthesis restores naturalistic speech

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.