Meta Unveils 'Imagine Me': AI-Powered Self-Image Generation Tool for Facebook and Instagram

Meta AI's new 'Imagine Me' tool will let you generate AI images of yourself

Meta has introduced a new feature called "Imagine Me," which lets users create AI-generated images based on their photos and prompts. This tool, currently in beta in the US, lets users type prompts like "Imagine me as a superhero" or "Imagine me in a historical setting," and the AI generates a customized image accordingly. With "Imagine Me," US-based users can simply type the command in the chat to start creating their personalized images. According to Meta, the AI can seamlessly edit photos, add or remove objects, and make other modifications. Powered by the new Llama 405B model, users can also generate silly images, such as "Me as a 3D sticker," and easily modify them by typing instructions like "Change to a royal image." This intuitive interaction aims to make AI-powered creativity accessible and fun. This feature is part of a broader update to Meta AI, which now supports more languages and is available in 22 countries such as Argentina, Chile, Colombia, Ecuador, Mexico, Peru, and Cameroon. As stated above, the feature is currently in beta, but the company plans on committing to bi-weekly updates of its AI. Next month, Meta plans to introduce an "Edit with AI" button, further simplifying photo editing.

Meta AI's New 'Imagine Me' Tool Will Let You Generate AI Images Of Yourself

Meta has introduced a new feature called "Imagine Me," which lets users create AI-generated images based on their photos and prompts. This tool, currently in beta in the US, lets users type prompts like "Imagine me as a superhero" or "Imagine me in a historical setting," and the AI generates a customized image accordingly. With "Imagine Me," US-based users can simply type the command in the chat to start creating their personalized images. According to Meta, the AI can seamlessly edit photos, add or remove objects, and make other modifications. Powered by the new Llama 405B model, users can also generate silly images, such as "Me as a 3D sticker," and easily modify them by typing instructions like "Change to a royal image." This intuitive interaction aims to make AI-powered creativity accessible and fun. This feature is part of a broader update to Meta AI, which now supports more languages and is available in 22 countries such as Argentina, Chile, Colombia, Ecuador, Mexico, Peru, and Cameroon. As stated above, the feature is currently in beta, but the company plans on committing to bi-weekly updates of its AI. Next month, Meta plans to introduce an "Edit with AI" button, further simplifying photo editing.

Meta AI's new 'Imagine Me' tool will let you generate AI images of yourself

Meta has introduced a new feature called "Imagine Me," which lets users create AI-generated images based on their photos and prompts. This tool, currently in beta in the US, lets users type prompts like "Imagine me as a superhero" or "Imagine me in a historical setting," and the AI generates a customized image accordingly. With "Imagine Me," US-based users can simply type the command in the chat to start creating their personalized images. According to Meta, the AI can seamlessly edit photos, add or remove objects, and make other modifications. Powered by the new Llama 405B model, users can also generate silly images, such as "Me as a 3D sticker," and easily modify them by typing instructions like "Change to a royal image." This intuitive interaction aims to make AI-powered creativity accessible and fun. This feature is part of a broader update to Meta AI, which now supports more languages and is available in 22 countries such as Argentina, Chile, Colombia, Ecuador, Mexico, Peru, and Cameroon. As stated above, the feature is currently in beta, but the company plans on committing to bi-weekly updates of its AI. Next month, Meta plans to introduce an "Edit with AI" button, further simplifying photo editing.

Meta AI's new 'Imagine Me' tool will let you generate AI images of yourself

Meta has introduced a new feature called "Imagine Me," which lets users create AI-generated images based on their photos and prompts. This tool, currently in beta in the US, lets users type prompts like "Imagine me as a superhero" or "Imagine me in a historical setting," and the AI generates a customized image accordingly. With "Imagine Me," US-based users can simply type the command in the chat to start creating their personalized images. According to Meta, the AI can seamlessly edit photos, add or remove objects, and make other modifications. Powered by the new Llama 405B model, users can also generate silly images, such as "Me as a 3D sticker," and easily modify them by typing instructions like "Change to a royal image." This intuitive interaction aims to make AI-powered creativity accessible and fun. This feature is part of a broader update to Meta AI, which now supports more languages and is available in 22 countries such as Argentina, Chile, Colombia, Ecuador, Mexico, Peru, and Cameroon. As stated above, the feature is currently in beta, but the company plans on committing to bi-weekly updates of its AI. Next month, Meta plans to introduce an "Edit with AI" button, further simplifying photo editing.

Meta Launches AI Selfie Generator 'Imagine Me'

Meta has introduced its new AI-generator "Imagine Me" which allows users to create images based on their photos. Meta AI, the company's AI-powered assistant, is available across Facebook, Instagram, Messenger, WhatsApp, and the web. In a blog post published on Tuesday, Meta announced the roll-out of Meta AI image generator "Imagine Me" to all of its platforms. The new "Imagine Me" feature, which is now available in beta in the U.S., allows users to create images based on their photos and a prompt like "Imagine me as an Astronaut" or "Imagine me as a 3D sticker." The new "Imagine Me" tool utilizes Meta's cutting-edge personalization model. U.S.-based Meta AI users simply need to type "Imagine Me" in the chat to access Meta's AI Image generator feature. Users then need to add a prompt like "Imagine me as a royalty" or "Imagine me in a surrealist painting" to create images. "Have you ever dreamed of being a superhero, a rockstar, or a professional athlete? Now, you can see yourself in a whole new light with 'Imagine me' prompts in Meta AI -- a feature we're starting to roll out in beta in the U.S. to start," Meta writes in the blog post. "Imagine yourself creates images based on a photo of you and a prompt like 'Imagine me surfing' or 'Imagine me on a beach vacation' using our new state-of-the-art personalization model." On Threads, Meta CEO Mark Zuckerberg shared four images of himself created on the company's Imagine Me tool and asked his followers to select the best AI-generated photo out of them. The images showed Zuckerberg wearing comedically large gold chains, onstage looking like a member of a boy band, resembling a streetwear designer, and dressing like a "video game character" in a blue cap and vest. Meta also announced a range of new editing tools that lets users add or remove objects as well as change, and edit the images created with Imagine Me. "It'll also be easier to create your ideal image with Meta AI thanks to new creative editing capabilities," Meta writes. "You can easily add or remove objects, change them and edit them -- adjusting just what you want while keeping the rest of the image as it was. You could say 'Imagine a cat snorkeling in a goldfish bowl' and then decide you want it to be a corgi. "So you'd simply write 'Change the cat to a corgi' to adjust the image. And next month, you'll see the addition of an Edit with AI button that you can use to fine-tune your imagined images even further." According to TechCrunch, Meta did not reveal what data it used to create Imagine Yourself. But the company's terms of use make it clear that public posts and images on its platforms are fair game -- something which has not sat well with users, especially photographers. Last month, scores of photographers signed an open letter rallying against Meta's plan to use public photos on Instagram and Facebook to train its AI tools.

Meta AI's latest feature can show you in a fantasy world - if you feed it your face

Meta is opening up access to the Meta AI assistant geographically, linguistically, and artistically, giving it the ability to communicate in seven new languages and seven additional countries, and create fantasy images of you based on prompts. Users in 22 countries can now interact with Meta AI on WhatsApp, Instagram, Messenger, and Facebook, and the chatbot now understands and can respond in French, German, Hindi, Hindi-Romanized Script, Italian, Portuguese, and Spanish. Meta AI will also appear for the first time to those wearing Ray-Ban Meta smart glasses and Meta Quest headsets. The expansion also includes a new AI image creation tool called "Imagine Me" that will produce a digital avatar of the user based on uploaded photos. The virtual version of the user can then be embedded in any setting desired through a text prompt. If you don't like what the AI comes up with, you can submit a follow-up prompt that will change whatever aspect doesn't match your vision for the AI-generated art. "Simply type "Imagine me" in your Meta AI chat to get started, and then you can add a prompt like "Imagine me as royalty" or "Imagine me in a surrealist painting." From there, you can share the images with friends and family, giving you the perfect response or funny sidebar to entertain your group chat," Meta explained in the update announcement. "You can easily add or remove objects, change them and edit them -- adjusting just what you want while keeping the rest of the image as it was. You could say "Imagine a cat snorkeling in a goldfish bowl" and then decide you want it to be a corgi. So you'd simply write "Change the cat to a corgi" to adjust the image." Meta had been testing the Imagine Me feature on WhatsApp, but it will now roll out across all of the tech giant's platforms. In addition, any AI art produced with Meta's tools will soon be sharable on Facebook posts and stories, as well as through messages on Instagram, Messenger, and WhatsApp. One upgrade that won't be universally available right now is access to Meta's most advanced AI model, Llama 405B, which will enhance the assistant's ability to tackle complex questions, particularly in math and coding, but only on WhatsApp and meta.ai for now. Still, it's the Imagine Me and related AI image editing tools that are the standout aspect of the upgrade. It's not something Meta's rivals are offering right now, instantly opening a channel to entice some OpenAI and Google fans to switch to Meta. Frankly, ChatGPT and Google Gemini will rarely create AI images of real people and definitely won't store a model to reuse. They tend to suggest a general look for an AI-generated image of a human if they even allow it all.

Meta AI gets new 'Imagine me' selfie feature | TechCrunch

Meta AI, Meta's AI-powered assistant across Facebook, Instagram, Messenger, and the web, can now speak in more languages and create stylized selfies. And, starting today, Meta AI users can route questions to Meta's newest flagship AI model, Llama 3.1 405B, which the company says can handle more complex queries than the previous model underpinning Meta AI. The question is whether the enhancements will be enough to improve the overall Meta AI experience, which many reviewers, including TechCrunch's Devin Coldewey, found incredibly underwhelming at launch. The early iterations of Meta AI struggled with facts, numbers, and web search, often failing to complete basic tasks like looking up recipes and airfares. Llama 3.1 405B could make a difference, potentially. Meta claims that the new model is particularly adept at math and coding questions, making it well-suited for help with math homework problems, explaining scientific concepts, code debugging and so on. However, there's a catch. Meta AI users have to manually switch to Llama 3.1 405B in order to use it, and they're limited to a certain number of queries each week before Meta AI automatically switches over to a less-capable model (Llama 3.1 70B). Meta's labeling the Llama 3.1 405B integration as a "preview" for the time being. There's another new generative AI model besides Llama 3.1 405B in Meta AI, and it powers the selfie feature. The model, called Imagine Yourself, creates images based on a photo of a person and a prompt like "Imagine me surfing" or "Imagine me on a beach vacation." Available in beta, Imagine Yourself can be invoked in Meta AI by typing "Imagine me" followed by anything that isn't NSFW. Meta didn't say which data was used to train Imagine Yourself, but the company's terms of use make it clear that public posts and images on its platforms are fair game. That policy -- and the convoluted opt-out process -- hasn't sat well with all users. Joining Imagine Yourself in Meta AI are new editing tools that let users add or remove, change or edit objects with prompts like "Change the cat to a corgi." Starting next month, Meta AI will get an "Edit with AI" button to pull up additional fine-tuning options. And in the coming days, Meta AI users will start seeing new shortcuts for sharing Meta AI-generated images to feeds, stories and comments across Meta apps, Meta says. Meta AI is also replacing the Meta Quest's VR headset's Voice Commands feature, with the rollout scheduled for next month in the U.S. and Canada in "experimental mode." Users will be able to use Meta AI with passthrough enabled to ask questions about things in their physical surroundings, Meta says, for example "Look and tell me what kind of top would complete this outfit" while holding up a pair of shorts. As of today, Meta AI is available in 22 countries, Meta says -- new additions include Argentina, Chile, Colombia, Ecuador, Mexico, Peru and Cameroon. The assistant now supports French, German, Hindi, Hindi-Romanized Script, Italian, Portuguese and Spanish, and Meta promises that more languages are on the way.

Mark Zuckerberg's Meta levels up with exciting new AI model

The new AI model is currently available in beta but it may be rolloed out to Meta apps in coming days Mark Zuckerberg's updated version of Meta AI, which is available on social media platforms owned by the company, can now do way more than you may have expected from it. According to TechCrunch, Meta's AI-powered assistant has recently been updated with a plethora of improvements, including the introduction of the new "Imagine Yourself" generative AI model. But what does the new AI model do and how does it work? The new generative AI model in Meta AI powers a new feature which create stylised selfies, according to TechCrunch. The model, called Imagine Yourself, creates images based on a photo of a person and can be prompted by typing "Imagine me" followed by anything that is not "not safe for work" (NSFW). Imagine Yourself is available in beta and Meta has not revealed which data was used to train this AI model. However, the company's terms of use make it clear that public posts and images on its platforms are fair game, according to TechCrunch. Meta AI is also introducing new editing tools allowing users to add, remove, change or edit objects using simple prompts. A new "Edit with AI" button will be available next month, providing additional fine-tuning options. Users will also have new shortcuts for sharing Meta AI-generated images to feeds, stories and comments across Meta apps in coming days, Meta says.

Now, you can create real personalised images on WhatsApp with Meta AI: Mark Zuckerberg unveils new feature

Meta CEO Mark Zuckerberg has unveiled updates to Meta AI, allowing users to generate personalized images of themselves in various settings and styles. This new feature enables individuals to visualize themselves in different scenarios, such as a gladiator or a boy band member. Zuckerberg demonstrated the feature by sharing a video on Instagram. He scanned his face using Meta AI and requested images of himself as a gladiator and a boy band member, including one with a large gold chain. The results were realistic but clearly identifiable as AI-generated. Meta AI is now accessible in additional countries, including Argentina, Chile, Colombia, Ecuador, Mexico, Peru, and Cameroon. The updated AI also supports multiple languages, such as Hindi, Spanish, French, Portuguese, German, and Italian. Meanwhile, Mark Zuckerberg's image featuring him working at a desk surrounded by various peripherals has recently gone viral on social media. Users are connecting with the everyday scene, while others are intrigued by the gadgets visible in the photo. To celebrate Facebook's 20th anniversary, Zuckerberg was photographed working at a desk with a laptop elevated on a stack of books and several pairs of glasses scattered across the table. This image quickly garnered attention online, with many speculating about the presence of the glasses. Some believe the glasses could be Meta's upcoming augmented reality (AR) glasses, known as Orion, which have yet to be officially released. Reports suggest these AR glasses might be unveiled at Meta Connect later this September, according to The Sun. The timing of Zuckerberg's photo coincides with Meta's recent announcements about its forthcoming AR glasses. The desk setup and the rumored glasses have sparked significant interest among Meta users, heightening anticipation for the anticipated product launch.

Meta AI is now available in Spanish, Portugese, French and more

Meta AI launched in September 2023 using the Llama 2 learning language model. Nearly a year later, Meta has announced a new round of features for its AI assistant and a fresh LLM to support it: Llama 3.1. These updates include an expansion of who can access Meta AI. Thanks to the addition of Argentina, Chile, Colombia, Ecuador, Mexico, Peru and Cameroon, the assistant is now available in 22 countries. It's also accessible in new languages: French, German, Hindi, Hindi-Romanized Script, Italian, Portuguese, and Spanish. However, some of the new features are location or language-specific for the time being. Meta is rolling out a beta tool called "Imagine me" throughout the US. It allows for prompts such as "Imagine me surfing" or "Imagine me as a surrealist painting," and the AI assistant will create it using a photo of the individual. Meta is also adding new ways to tinker with an image, such as removing, changing or editing its content. This feature allows for creating an image, such as a duck, with the "Imagine me" tool and then instructing Meta AI to "Change the duck to a cat." Next month there will also be an "Edit with AI" button for further fine-tuning of images. The company is also rolling out the ability to create an image with Meta AI in a feed, comment, story or message across Facebook, Instagram, WhatsApp and Messenger. It should roll out this week, though just in English for now. Then there's the launch of Llama 3.1 405B -- Meta's new open-source AI model. You can use it on WhatsApp or meta.ai for tasks such as answering math problems and coding. Meta claims it will update its AI technology every two weeks and that new features and languages are on the way.

Meta Platforms : AI Is Now Multilingual, More Creative and Smarter

You now have the option to use our largest and most capable open-source model inside Meta AI for your tough math and coding questions and more complex projects. We're expanding access toMeta AI- the assistant in our apps and devices - and introducing new features to help you with answers, ideas and inspiration. Meta AI is now available in 22 countries, with the newest today in Argentina, Chile, Colombia, Ecuador, Mexico, Peru and Cameroon. You can also interact with Meta AI across WhatsApp, Instagram, Messenger and Facebook in new languages: French, German, Hindi, Hindi-Romanized Script, Italian, Portuguese and Spanish with more to come. [Link] With Meta AI across WhatsApp, Instagram, Messenger, Facebook andmeta.ai, people are tapping into the power of AI to get more done in less time, bring creative ideas to life and expand their knowledge. From tackling how-to tasks and answering questions to providing inspiration and guidance, Meta AI has enhanced people's daily routines and been a creative partner to lean on. This is just the start - we're listening to your feedback, updating Meta AI every two weeks to enhance your experience and innovating quickly to bring new features to help you create, get inspired and get more done. Have you ever dreamed of being a superhero, a rockstar or a professional athlete? Now, you can see yourself in a whole new light with "Imagine me" prompts in Meta AI - a feature we're starting to roll out in beta in the US to start. Imagine yourself creates images based on a photo of you and a prompt like 'Imagine me surfing' or 'Imagine me on a beach vacation' using our newstate-of-the-art personalization model. Simply type "Imagine me" in your Meta AI chat to get started, and then you can add a prompt like "Imagine me as royalty" or "Imagine me in a surrealist painting." From there, you can share the images with friends and family, giving you the perfect response or funny sidebar to entertain your group chat. It'll also be easier to create your ideal image with Meta AI thanks tonew creative editing capabilities. You can easily add or remove objects, change them and edit them - adjusting just what you want while keeping the rest of the image as it was. You could say "Imagine a cat snorkeling in a goldfish bowl" and then decide you want it to be a corgi. So you'd simply write "Change the cat to a corgi" to adjust the image. And next month, you'll see the addition of an Edit with AI button that you can use to fine tune your imagined images even further. [Link] Want to add an image made with Meta AI to your Facebook post? We're starting to roll out the ability for you to create it right within feed, stories, comments and messages across Facebook, Instagram, Messenger and WhatsApp - anywhere Meta AI is available in English starting this week. And soon you'll be able to do this in more places across our apps and in more languages as well. This slideshow requires JavaScript. You now have the option to use our largest and most advanced open-source model inside of Meta AI on WhatsApp andmeta.ai.Llama 405B's improved reasoning capabilities make it possible for Meta AI to understand and answer your more complex questions, especially on the topics of math and coding. You can get help on your math homework with step-by-step explanations and feedback, write code faster with debugging support and optimization suggestions, and master complex technical and scientific concepts with expert instruction. This slideshow requires JavaScript. You can combine Meta AI's coding expertise and image generation capabilities to build a new game from scratch or put a fresh spin on a classic favorite. Turn your wild idea into a reality in just minutes, and even put yourself right into the game. [Link] While today's other updates are specific to Meta AI in our apps and on the web, Meta AI is also available on Ray-Ban Meta smart glasses and starting toroll out next month on Meta Questin the US and Canada in experimental mode. Meta AI will replace the current Voice Commands on Quest, allowing you to control your headset hands-free, get answers to questions, stay up to date with real-time information, check the weather and more. You can also use Meta AI with Vision in Passthrough to ask questions about things you see in your physical surroundings. Let's say you're watchingYouTubevideos of some breathtaking hikes in mixed reality while packing for your upcoming trip to Joshua Tree. You can ask Meta AI for advice on how to best dress for the summer weather. Or you could hold up a pair of shorts and say, "Look and tell me what kind of top would complete this outfit." You can get the forecast so you can prep for the weather ahead and even ask for local restaurant recommendations to indulge your inner foodie.

Mark Zuckerberg unveils Meta AI visualisation feature: 'Imagine me as gladiator'

Also Read: Bill Gates wants 'smart' Elon Musk to speak on this issue more: 'He talks a lot but...' This new feature is also available in multiple regions, supporting various languages. Also Read: Budget 2024: How your SIPs will be taxed after capital gains rate changes Zuckerberg has released a video of the entire process on Instagram where he scans his face using Meta AI and asks it to visualise him as a gladiator, a boy band member afterwards, and then, as wearing a big gold chain. This comes at a time when the billionaire CEO also said in a recent Bloomberg interview that AI clones can help content creators to engage with their fans more easily by handling aspects such as responding to comments and messages, which would free up time for creators to focus on making content. Mark Zuckerberg also announced that Meta AI is now available in more countries such as Argentina, Cameroon, Chile, Colombia, Ecuador, Mexico, and Peru. Meta AI now support languages like Hindi, French, German, Italian, Portuguese, and Spanish.

The Quest 3 is getting a personal assistant courtesy of Meta AI

It's been a big day for Meta. First off, the tech giant rolled out several new features to Meta AI. And now the same AI model is coming to Quest headsets next month. According to the company's release video, Meta AI will function as a personal assistant of sorts on the virtual reality headset. You can ask it any burning questions you have and it'll answer in real-time with information obtained through Bing. It can recite memorable lines from Shakespeare's plays or give brief lectures on American history. Through Meta AI with Vision, the headset can detect objects, people, and more in front of its cameras and then provide a contextual answer to these inquiries. For example, users can instruct the assistant to translate text into another language, give fashion tips for the summer, or identify what's in front of it. The AI can even detect dogs, as shown in the video. Meta AI on Quest is experimental software that is seeing a limited released in the United States and Canada. To try it out, you'll have to enter the settings menu on your headset and select "Experimental". You should see and be able to "toggle [the] features there." Because this is experimental, users will not experience Meta AI's full capabilities. The Vision feature will be available via Passthrough on the Quest 3 and Quest Pro headsets, but it will not work in virtual reality mode. Meta states, "virtual objects are not recognized at this time," although judging from the wording, this could change. A Meta spokesperson confirmed that the Quest 2 will lack Vision "because it does not have color passthrough." Also, to make room, the company states that Meta AI will replace Voice Commands as users' main way to interact with the headset. Voice Commands will be widely deprecated at some point in the future, although they'll stay if you don't try out the AI model. Details on what will happen to Voice Commands are scarce at the moment. The Meta spokesperson didn't provide additional information.