Latest news with #Veo
Yahoo
8 hours ago
- Entertainment
- Yahoo
YouTube Adds More Gen AI Features to Shorts
This story was originally published on Social Media Today. To receive daily news and insights, subscribe to our free daily Social Media Today newsletter. YouTube's bringing more generative AI features to Shorts, by integrating its latest Veo image animation and conversion tools into the Shorts process. First off, YouTube's rolling out image-to-video animation, which can turn your photos into animated elements. As explained by YouTube: 'Bring your story to life with Photo to video, which instantly turns a picture from your camera roll into a video. Just select your image, choose a creative suggestion, and watch your memories come alive.' This has been a trending use case for several AI tools, with users posting videos expanded from photos to create all-new scenes. On another front, YouTube's adding an option to animate drawings, or convert your still images into alternate settings. So now, you can immediately flesh out and/or animate your sketches and doodles, with little effort. Thus far, this hasn't proven as popular as photo animation, but it's another way to utilize AI within the Shorts creation process. Along the same line, YouTube's also launching 'AI Playground,' which will house various new AI experiences that you can test and experiment with. 'Inside, you'll find our latest gen AI creation tools, a gallery of inspirational examples, and pre-filled prompts to help you instantly generate videos, images, music, and more. Find AI playground by tapping the create button and then the sparkle icon in the top right corner. It's available now for everyone in the United States, Canada, Australia, and New Zealand to start.' It's another option to showcase Google's evolving gen AI tools, providing direct access to its latest models, and what they can do. And this is just the start. Google says that all of its image-to-video and generative effects are currently powered by Veo 2, but will be upgraded to Veo 3 shortly, making them even more responsive. YouTube also notes that all of its gen AI features will utilize SynthID watermarks, and will be clearly labelled to indicate that they were AI generated. Some interesting options, which will likely prove popular, and could give you some new ways to express your IDs through YouTube's improving AI processes. Image-to-video is rolling out over the next week in the US, Canada, Australia, and New Zealand, with more regions coming later this year. When they're available to you, the new AI features will be in the 'Effects' section in the Shorts camera. Recommended Reading YouTube Shares Insights Into the Potential of Gen AI for Creators
Hans India
9 hours ago
- Hans India
Google Expands AI Photo-to-Video Tools to Google Photos and YouTube Shorts
Google is expanding its AI-powered photo-to-video capability to more of its popular apps, giving users new ways to transform static memories into dynamic clips. After debuting its Veo 3-powered tool in the Gemini app earlier this month, Google is now rolling out a similar feature to Google Photos and YouTube Shorts—though this time, the tools run on Google's older Veo 2 video model and come with a few extra limitations. In Google Photos, the AI tool can turn selected photos into short, six-second videos. Meanwhile, YouTube Shorts users will have more flexibility, with the ability to choose their desired clip length. One notable difference is that, unlike in Gemini or the standalone Veo 2 experience, these new tools won't let users write their own prompts to guide what the video looks like. Instead, users must pick from preset prompts like 'Subtle movements' or 'I'm feeling lucky' in Google Photos. The new AI video feature is rolling out starting today in the US for Google Photos on both Android and iOS devices. YouTube Shorts users in the US, Canada, Australia, and New Zealand can expect access within the week. Google is also introducing a Remix tool for Google Photos that gives photos a fresh twist. Users will soon be able to transform pictures into different styles—think anime, comic books, sketches, or even 3D animations. The Remix and photo-to-video tools will live under a new Create tab in the Photos app, which Google plans to launch in the US next month. This new section will gather all creative tools—like collages, highlight videos, and more—into one easy-to-find place. Google reminds users that these new generative AI features are still 'experimental,' so results may vary. The company encourages people to give feedback by giving thumbs up or down on generated content, which will help refine the technology over time. Every AI-generated video or image will include Google's invisible SynthID digital watermark, while videos made in Google Photos will also show a visible watermark, so it's clear at a glance that they're AI-created. This latest update extends Google's lead in generative AI for photos, far surpassing Apple's more cautious approach. Apple's Image Playground tool, for example, deliberately avoids photorealistic generation to limit risks like deepfakes and misinformation.
Deccan Herald
12 hours ago
- Business
- Deccan Herald
Google I/O Connect India Highlights: Gemini 2.5 Flash, Gemma 3n and more
'Indian developers are literally writing the next chapter of India's success story, using AI capabilities to build real-world applications that are reaching millions of businesses and people across India and the world. We have been inspired by their solutions, and proud that many have chosen our AI, including Gemini, Gemma and GenMedia models like Veo and Imagen, to build their innovations. As we have done today, we remain steadfast in bringing them our industry-leading, cuing-edge capabilities to accelerate their journeys, and India's leadership in a global AI-led future.'
Tom's Guide
4 days ago
- Tom's Guide
I used Google's Veo 3 to create AI ASMR food videos
Google's Veo 3 AI video model is a league above any of its competitors for one key reason — sound. You can prompt not just what you see on screen, but also what you hear. Built by Google's DeepMind lab, the first Veo model debuted in May 2024, and each new generation has added more functionality. It has always excelled in motion accuracy and physics understanding compared to competitors, but the addition of sound was a game-changer. You can use it to prompt a short commercial, a scene from a movie you're writing, or even a music video. But there's one use I've seen more than any other — ASMR (autonomous sensory meridian response): those gentle tapping, whispering, and ambient sounds that trigger a tingling sensation for some people. To see just how far this could go, I created a series of ASMR food prompts — each designed to generate a matching video and sound around something culinary. Veo 3 is now available in the Gemini app. Just select the Video option when starting a new prompt, type what you want, and an 8-second clip is generated. While Gemini isn't necessarily the best way to access Veo 3 — I'd recommend Freepik, Fal, Higgsfield, or Google Flow — it's easy to use and gets the job done. A key advantage of using Gemini directly is that it automatically interprets and enhances your prompts. So if you ask for 'a cool ASMR video featuring lasagna,' that's what you'll get. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. You can also be more specific using something called structured prompting — labeling each moment with timestamps and scene descriptions. But unless you need precise control, a simple paragraph (aka narrative prompting) is usually more effective. The first task in any AI project is thinking about your prompt. Models are getting better at interpreting intent, but it's still better to be specific if you know what you want. I knew I wanted ASMR food videos, so I started with a test: 'ASMR food video with sound.' The result? Decent. It essentially gave me the lasagna I had in mind. Then I refined it — outlining specific food types, adding sound descriptions, and even trying a structured prompt for a fizzy drink with ice. Most of the time, narrative prompts work best. Just describe what you want to see, the flow of the video, and how sound should come through. The first prompt, 'ASMR food video with sound,' produced a stunning clip of someone sliding a fork into a slice of lasagna. You hear the squish as the fork enters, then the clunk as it hits the plate. This is one case where I wish Veo 3 had an 'extend clip' button. There was no other prompting involved, so I had no way of identifying what the food would be, how the sound would come out or even if the sound would work. This is why it's important to be specific when prompting AI models, even ones in chatbots like Gemini. Next, I went more specific — a longer, narrative-style prompt asking Veo 3 to generate a close-up of a chef preparing and eating satisfying food in a well-lit kitchen. I asked for slow-motion visuals of ingredients being chopped, the sizzling sound of butter melting in a pan, and a crunch as the chef takes a bite. I also added this line: 'Emphasize audio quality: clean, layered ASMR soundscape without music' to direct not just the sound, but to the style of sound and what I don't want to hear. For the final prompt I started with an image. I used Midjourney v7 to create a picture of a woman looking at rainbow popcorn, then added the prompt 'ASMR food' in Gemini. Visually, the result was stunning — but for some reason, the woman says in a voiceover, 'This is delicious, this rainbow popcorn.' That's on me — I didn't specify whether she should speak, or what she should say. A simple fix: put any speech you want in quotes. For example, I could have prompted her to say 'I love to watch popcorn pop,' and emphasized the word pop. I also could've specified that she was speaking on camera — and Veo 3 would have synced the lip movement to match. Overall, Veo 3 delivers impressive results, especially when it comes to generating high-quality sound that accurately reflects the visuals. While there are a few quirks to navigate, like unintended voiceovers or slightly underbaked looking lasagna — these are easily addressed with more specific prompting.
Engadget
6 days ago
- Entertainment
- Engadget
Engadget Podcast: Ancestra director Eliza McNitt defends AI as a creative tool
Eliza McNitt is no stranger to new media. Her 2017 project, Fistful of Stars , was a fascinating look at stellar birth in virtual reality, while her follow-up Spheres explored black holes and the death of stars. Now with her short film Ancestra , McNitt has tapped into Google's AI tools to tell a deeply personal story. Working with Google Deepmind and director Darren Aronofsky's studio Primordial Soup, McNitt used a combination of live-action footage and AI-generated media to tell the story of her own traumatic birth. The result is an uncanny dramatic short where the genuine emotion of the live-action performance wrestles agains the artificiality of AI imagery. The film begins when the lead's (Audrey Corsa, playing McNitt's mother) routine natal care appointment turns into an emergency delivery. From that point on we hear her opine on how her child and all living things in the universe are connected — evoking the poetic nature of Terrence Malick's films. We jump between Corsa's performance, AI footage and macro- and micro-photography. In the end, Corsa holds a baby that was inserted by Google's AI, using prompts that make it look like McNitt as an infant. To view this content, you'll need to update your privacy settings. Please click here and view the "Content and social-media partners" setting to do so. There's no escaping the looming shadow of Google's AI ambitions. This isn't just an art film — it's an attempt at legitimizing the use of AI tools through McNitt's voice. That remains a problem when Google's models, including Veo and other technology from DeepMind, have been trained on pre-existing content and copyrighted works. A prestigious short coming from Darren Aronofsky's production studio isn't enough to erase that original sin. "I was challenged to create an idea that could incorporate AI," McNitt said in an interview on the Engadget Podcast. "And so for me, I wanted to tell a really deeply personal story in a way that I had not been able to before... AI really offered this opportunity to access these worlds where a camera cannot go, from the cosmos to the inner world of being within the mother's womb." This embedded content is not available in your region. When it comes to justifying the use of AI tools, which at the moment can credibly be described as plagiaristic technology, McNitt says that's a decision every artist will have to make for themselves. In the case of Ancestra , she wanted to use AI to accomplish difficult work, like creating a computer generated infant that looked like her, based on photos taken by her father. She found that to be more ethical than bringing in a real newborn, and the results more convincing than a doll or something animated by a CG artist. "I felt the use of AI was really important for this story, and I think it's up to every artist to decide how they wanna use these tools and define that," she said. "That was something else for me in this project where I had to define a really strong boundary where I did not want actors to be AI actors, [they] had to be humans with a soul. I do not feel that an performance can be recreated by a machine. I do deeply and strongly believe that humanity can only be captured through human beings. And so I do think it's really important to have humans at the center of the stories." To that end, McNitt also worked with dozens of artists create the sound, imagery and AI media in Ancestra . There's a worry that AI video tools will let anyone plug in a few prompts and build projects out of low-effort footage, but McNitt says she closely collaborated with a team of DeepMind engineers who crafted prompts and sifted through the results to find the footage she was looking for. (We ran out of time before I could ask her about the environmental concerns from using generative AI, but at this point we know it requires a significant amount of electricity and water. That includes demands for training models as well as running them in cloud.) To view this content, you'll need to update your privacy settings. Please click here and view the "Content and social-media partners" setting to do so. "I do think, as [generative AI] evolves, it's the responsibility of companies to not be taking copyrighted materials and to respect artists and to set those boundaries, so that artists don't get taken advantage of," McNitt said, when asked about her thoughts on future AI models that compensate artists and aren't built on stolen copyrighted works. "I think that that's a really important part of our role as humans going forward. Because ultimately, These are human stories for other human beings. And so it's, you know, important that we are at the center of that." If you buy something through a link in this article, we may earn commission.
