Nano Banana, the viral image generation and editing model Google released in August as part of Gemini 2.5 Flash, has been used to generate more than 5 billion images to date, and now Google is looking to increase its usage by introducing the model to other popular services. Officially known as Gemini 2.5 Flash Image, the visual tool is now available in Google Search via a Create tab that activates it in Google Lens and AI Mode. It’s also been incorporated into NotebookLM, powering the Video Overviews tool that transforms documents into narrated explainer videos. The company says Nano Banana is also coming soon to Google Photos. Continue reading Nano Banana AI Image Tool Is Added to Search, NotebookLM

Microsoft is teasing a bespoke AI image generator. The model, called MAI-Image-1, was designed in-house and works using text prompts. It is the third AI model Microsoft has debuted this year, following MAI-Voice-1 and MAI-1-preview, both released in August. The company, which is OpenAI’s largest investor, has been seeking to put some breathing room between itself and the startup to better position the fledgling firm for independence and profitability. And products exclusive to Microsoft surely won’t hurt that company’s bottom line. “We’re creating AI for everyone,” Microsoft says, calling MAI-Image-1 “the next step on our journey.” Continue reading Microsoft’s In-House AI Image Generator Receives High Marks

Google has released a free consumer version of the Veo-powered Vids generative video creation and editing tool that debuted in November 2024 as part of the Google Workspace productivity suite, a subscription product starting at $7 per month for individual users. Subscribers will continue to have access to a more full-featured Vids app, which has been updated with AI avatars, image-to-video capability and automatic transcript trimming that removes “filler words and awkward pauses with just a few clicks.” But the free tier provides basic AI-enhanced editing and video creation using templates that casual users will no doubt find helpful. Continue reading Google Releases Free Version of Veo 3-Powered Vids Editor

Grok Imagine is xAI’s new video and image generator, which is currently available via the X social platform, the Grok mobile app, and Grok web interface. Imagine replaces AI image generator Aurora, which was retired in May following a string of offensive posts that led to media criticism and user concerns. Despite the backlash, Elon Musk’s xAI seems determined to have Imagine push conventional limits, with a “spicy” mode that outputs imagery including adult content. Its text-to-image capabilities work with text or voice prompts, while the video tool relies on image prompts to make short clips using images from a user’s gallery or generated by Grok. Continue reading Grok Imagine from xAI Offers Video Generation, ‘Spicy’ Mode

AI startup Runway has a new tool called Game Worlds that lets users generate simple video game worlds using images and text-based prompts. At the moment, Runway Game Worlds can only help generate simple text-based interactive adventures that include pictures, but the company has plans to enable more complex game creation by the end of the year. Runway CEO Cristóbal Valenzuela says the company is interested in partnering with video game companies who are willing to provide game data that can be used to train the company’s models in exchange for generative capabilities. Continue reading Runway AI Intros Game Worlds Generator in Limited Preview

Chinese e-commerce giant Alibaba has released a new multimodal model called Qwen VLo that can understand and generate images. Available for free in preview through Qwen Chat, it can use image or text prompts to generate pictures, and accepts text in multiple languages, including Chinese and English. It can also edit, change backgrounds and switch styles, handling multiple image edits in sequence. An upgrade over January’s Qwen 2.5-VL release, Qwen VLo uses progressive generation, allowing users to see the image creation in progress, and Alibaba says it’s particularly good at making inline adjustments to fine-tune images. Continue reading Alibaba’s Qwen VLo Generative AI Shows Images in Progress

Google is celebrating 10 years of Google Photos by introducing a redesign of the Photos editor, including helpful new tools. The Photos editor gets some AI editing features previously available only on Pixel phones as part of its generative AI Magic Editor. The Photos platform is also expanding access to its AI-powered text-to-image Reimagine and automatic framing and related features first introduced with the Pixel 9. The company explains there are currently more than 1.5 billion monthly Photos users that have stored 9+ trillion photos and videos. The updates reflect Google’s AI push as it continues to integrate Gemini across its growing family of products and services. Continue reading Google Photos Rolling Out Redesign and New AI Editing Tools

TikTok AI Alive is a new image-to-video feature that can add sequential expression to selfies and add progressive hues to sunsets. Accessible through the platform’s Story Camera, AI Alive uses intelligent editing tools that give anyone, regardless of experience, “the ability to transform static images into captivating, short-form videos enhanced with movement, atmospheric and creative effects.” TikTok says it is prioritizing safety and transparency by adding a label to AI Alive stories, which will also have C2PA metadata embedded, traveling with the content even when it’s downloaded and shared elsewhere. Continue reading TikTok Offering ‘AI Alive’ Image-to-Video Generator in Stories

Online graphic design platform Freepik, has unveiled F Lite, a text-to-image generator that the company says was trained only on licensed content, making it safe for commercial use. The 10 billion-parameter F Lite — currently available in two openly-licensed versions — was developed in partnership with Fal.ai, a San Francisco-based AI startup that uses a proprietary inference engine and APIs to enable fast training, inference, and scaling of image, video, audio, and multimodal AI models. Freepik Head of AI Iván de Prado describes F Lite as “a significant milestone in open, responsible AI.” Continue reading Freepik Introduces a Responsibly Trained AI Image Generator

OpenAI has activated the multimodal image generation capabilities of GPT-4o, making it available to ChatGPT users on the Plus, Pro, Team and Free tiers. It replaces DALL-E 3 as the default image generator for the popular chatbot. GPT-4o’s accuracy with text, understanding of symbols and precision with prompts combined with well multimodal capabilities that allow the model to take cues from visual material have transformed its image capabilities from largely unpredictable to “consistent and context-aware,” resulting in “a practical tool with precision and power,” claims OpenAI. Continue reading OpenAI Delivers Native GPT-4o Image Generator to ChatGPT

Snapchat has introduced AI Video Lenses for those paying $16 per month for its Platinum tier. Powered by Snap’s custom-built generative video model, the initial three releases are a fox that perches on your shoulder, rambunctious racoons and a large bouquet of flowers with a zoom out effect. After selecting an AI Video Lens and applying it to a Snap, the AI video generates in the background, auto-saving save to Memories while users are free to continue messaging and Snapping on the app. The resulting video can be shared with friends or to Stories and Spotlight. Continue reading Snap Launches Generative AI Video Lenses for Platinum Subs

Alibaba has open-sourced its Wan 2.1 video- and image-generating AI models, heating up an already competitive space. The Wan 2.1 family, which has four models, is said to produce “highly realistic” images and videos from text and images. The company has since December been previewing a new reasoning model, QwQ-Max, indicating it will be open-sourced when fully released. The move comes after another Chinese AI company, DeepSeek, released its R1 reasoning model for free download and use, triggering demand for more open-source artificial intelligence. Continue reading Highly Realistic Alibaba GenVid Models Are Available for Free

Barely two weeks after the launch of its OmniHuman-1 AI model, ByteDance has released Goku, a new artificial intelligence designed to create photorealistic video featuring humanoid actors. Goku uses text prompts to create among other things, realistic product videos without the need for human actors. This last is a boon for ByteDance social media unit TikTok. Goku is open source, trained on a large dataset of roughly 36 million video-text pairs and 160 million image-text pairs. Goku’s debut is received as more bad news for OpenAI in the form of added competition, but a positive step for global enterprise. Continue reading ByteDance’s Goku Video Model Is Latest in Chinese AI Streak

Snap has created a lightweight AI text-to-image model that will run on-device, expected to power some Snapchat mobile features in the months ahead. Using an iPhone 16 Pro Max, the model can produce high-resolution images in approximately 1.4 seconds, running on the phone, which reduces computational costs. Snap says the research model “is the continuation of our long-term investment in cutting edge AI and ML technologies that enable some of today’s most advanced interactive developer and consumer experiences.” Among the Snapchat AI features the new model will enhance are AI Snaps and AI Bitmoji Backgrounds. Continue reading Snap Develops a Lightweight Text-to-Video AI Model In-House

Google DeepMind’s new Genie 2 is a large foundation world model that generates interactive 3D worlds that are being likened to video games. “Games play a key role in the world of artificial intelligence research,” says Google DeepMind, noting “their engaging nature, challenges and measurable progress make them ideal environments to safely test and advance AI capabilities.” Based on a simple prompt image, Genie 2 is capable of producing “an endless variety of action-controllable, playable 3D environments” — suitable for training and evaluating embodied agents — that can be played by a human or AI agent using keyboard and mouse inputs. Continue reading DeepMind Genie 2 Creates Worlds That Emulate Video Games