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

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs – Takara TLDR

DevOps automation startup SRE.ai launches with $7.2M in funding

China experiments with brain-computer interfaces to compete in AI race: report

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

I used Gemini to transform my old photos into video with Google’s Veo 3 — and the results surprised me

By Advanced AI EditorAugust 13, 2025No Comments7 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


There’s no way of escaping it at this point, but AI is everywhere and I’ve been embracing it a lot more. One of the coolest new AI features I’ve stumbled upon on my Galaxy Z Flip 7 pertains to the Google Gemini app and how it can generate short videos for me.

During Google I/O 2025, the company introduced its updated AI video generation model called Veo 3. What’s really remarkable about this AI tool is that it can generate high-quality videos by simply providing Gemini with a description of what you want — and it generates it complete with sound and music.

As a videographer and video editor, I can definitely see this helpful in so many ways by helping to create b-roll shots I could actually use. There’s also other neat stuff that Veo 3 could do, like using an existing photo and transforming it into a video. Here’s what I’ve been able to generate.


You may like

Veo 3: What You Need To Know

Google Gemini Veo 3 video generator screenshot.

(Image credit: Future)

Before I share what I’ve been able to generate with Veo 3, just know that I have a Google One subscription that bundles in Gemini Pro — which gives me access to Veo 3 Fast through the Gemini app.

Like I said, you can create videos by providing a description in the Gemini app, or upload an existing still photo to transform it to a video. It takes about one to two minutes for Gemini to create the clip, which is in 720p at 24 frames per second. That might not be high resolution compared to how ubiquitous 4K is today, but these are more than perfect for sharing on social media.

All of the videos that Veo 3 Fast generates have audio included, both background music and sound effects when appropriate for the clip. I was having a lot of fun asking Gemini to create these clips, up until it told me that I hit my daily limit — which I’ve found to be three a day at the moment. Hopefully this changes, but I can see this limit being different for what kind of subscription you’re on.

Running by the beach

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

For my first test, I asked Veo 3 to take an existing photo I took of myself and told Gemini to “mate it so that the person is running at the beach.” I’ll admit it looks pretty legit, albeit for the fact that the details are a bit too soft for my liking — but at least the video looks accurate.

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

From my backyard, I really like how the camera pans over to make it seem like the beach is right there. Not only does it properly generate my sunglasses and hat, even when the camera pans to my profile, I like how Veo 3 adds the sound of the waves hitting the sand and my running stride.

Telescope for astrophotography

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

I don’t know what happened with this second clip, but I think I should’ve started a new chat because it appears to think that I was referring to my previous description of running by the beach. Using a photo I’ve taken of my Unistellar Odyssey Pro smart telescope in my back yard, it instantly jumps to another entirely different shot of a person running by the beach at night.

I asked Gemini to “make it so that there’s an aurora in the sky,” thinking it was going to be exclusively for the photo I shot. Despite the mess up, which is partly my fault, it does generate the video. Just as before, the details are a bit softer than what I’d like, but at least the animation looks right.

Veo 3used to generate telescope with auroras.

(Image credit: Veo 3 AI generated / Tom’s Guide / John Velasco)

I tried it again with a fresh chat to Gemini, and this time, it generates exactly what I wanted. What’s interesting about this video generation is how it also applies ambient light to the rest of the scene, while also giving the surrounding trees and branches a little bit of animation.

Alien invasion

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

Now this one really jumps out, mainly for how it lays out the scene from the photo I provided. With a simple shot of the park I captured with my phone, I asked Gemini to “make it so that there’s an alien invasion happening in the scene.”

It starts off with the shot from my photo, but the camera quickly moves forward to the playground in the park with flying saucers overhead with laser beams. If you don’t look at the details, you might miss some of the oddities in the video — like how a couple spacecraft appear from nowhere. Despite this, it’s an example of how easily (and quickly) Veo 3 can create a video from a simple description.

Cat moving to the music

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

I asked Gemini to take a photo of my black cat resting on top of my Sony headphones and “make the cat wear the headphones on the table and rocking out to music.” The only movement applied to the photo is to my cat, but you can see how the headphones wobble a bit when he’s moving around.

Unfortunately, it failed at having him wear the headphones. Apart from that, it’s a charming video that has the most detail in my opinion.

Chester Bennington portrait

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

Up until this point, I have Gemini existing photos I’ve captured to create videos with Veo 3 Fast. With this next test, though, I downloaded a portrait of former Linkin Park lead singer Chester Bennington and asked it to “put him into a boxing ring fighting someone.”

I’m surprised that it even allowed me to take an existing photo of a celebrity, but it fails to do the rest. The only thing it ends up doing is applying a little bit of animation to Chester’s photo, failing to put him into a boxing ring. However, the audio has a ringside announcer speaking over the video to introduce the boxer.

Optimus Prime versus Donatello

Veo 3 videos created with Gemini App

(Image credit: Veo 3 AI generated / Tom’s Guide)

For my final request, I asked Gemini to generate a video from scratch with nothing more than a text description — so I didn’t upload any photo with my request .This time, I asked it to “make a video where Optimus Prime the Transformer is fighting Donatello from Teenage Mutant Ninja Turtles.”

I will say that this one looks more like an animated video than anything else, but it created exactly what I wanted. Not only are they squaring off, but Gemini is intelligent enough to know who Donatello is apart from the rest of the Ninja Turtles. I also like the special effects of the Optimus Prime’s blaster hitting Donatello.

Veo 3: Bottom Line

Google Gemini Veo 3 running on a Galaxy Z Flip 7.

(Image credit: Tom’s Guide / John Velasco)

I’ve never tried any AI video generator tool before, but this is definitely impressive. While there’s still work to remove some of those oddities in some of the clips, I have to say that it’s a quick and easy way to make custom videos.

In addition to the visuals, I think Veo 3 accurately applies sound effects to make them feel more believable. I’m curious what Google ends up doing, like whether or not there will be other subscriptions to give users more than 3 videos a day.

Follow Tom’s Guide on Google News to get our up-to-date news, how-tos, and reviews in your feeds. Make sure to click the Follow button.

More from Tom’s Guide

Today’s best Google Pixel 9 Pro XL deals



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleStability AI SDXL 1.0 beginners guide from set up to creation
Next Article Anthropic’s Claude AI model can now handle longer prompts
Advanced AI Editor
  • Website

Related Posts

PixVerse AI Effect Brings Oil Paintings to Life: Trending AI Video Generation Tool Analysis | AI News Detail

August 21, 2025

Grok Imagine AI is now free for all users, generate videos with Spicy Mode

August 20, 2025

Sora 2 was missing from GPT-5 — but it could be the biggest jump in AI video yet

August 20, 2025

Comments are closed.

Latest Posts

Tanya Bonakdar Gallery to Close Los Angeles Space

Ancient Silver Coins Suggest New History of Trading in Southeast Asia

Sasan Ghandehari Sues Christie’s Over Picasso Once Owned by a Criminal

Ancient Roman Villa in Sicily Reveals Mosaic of Flip-Flops

Latest Posts

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs – Takara TLDR

August 21, 2025

DevOps automation startup SRE.ai launches with $7.2M in funding

August 21, 2025

China experiments with brain-computer interfaces to compete in AI race: report

August 21, 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

  • Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs – Takara TLDR
  • DevOps automation startup SRE.ai launches with $7.2M in funding
  • China experiments with brain-computer interfaces to compete in AI race: report
  • IBM and NASA create first-of-its-kind AI that can accurately predict violent solar flares
  • Window Reopens, But Expect A Convoy, Not A Stampede

Recent Comments

  1. Eugeneder on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. Williamcrosy on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. Lewiszix on Trump’s Tech Sanctions To Empower China, Betray America
  4. TimsothyReaws on TEFAF New York Illuminates Art Week With Mastery Of Vivid, Radiant Color
  5. DennisLIt on Foundation AI: Cisco launches AI model for integration in security applications

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.