Google launches Nano Banana 2 Lite for fast, low-cost AI image generation
It creates 1K images in about four seconds and costs about $0.034 per image
Image generation articles
Google is making AI images easier to create, and deepfakes easier to spot
Google Pics is a new AI photo editor, meanwhile SynthID and C2PA watermarking gets added to Search and Chrome
AI images are getting harder to spot, but physics still gives them away if you know where to look
Measuring perspective lines can identify AI photos, researchers say
Image generation is now the feature that moves the needle for AI apps
What gets people to download an AI app in 2026 has less to do with smarter models and more to do with images
Google upgrades Gemini image generation to Nano Banana 2 with 4K support
4K rendering, multimodal workflows, and C2PA-compatible SynthID watermarking built in
xAI launches Grok Imagine 1.0 with 10-second 720p video generation – here's what it looks like
xAI also released its image generating API and merged with SpaceX
Microsoft's new image generator shows it's ready to go its own way on AI
MAI-Image-1 model can turn text into realistic images – and it was built without outside help
Google unveils Gemini's "nano banana" model, taking AI image generation to the next level
Will Nano Banana do for Google what Ghibli images did for GPT?
What just happened? Google has just unveiled a major upgrade to Gemini AI's image generation capabilities. Gemini 2.5 Flash, a.k.a. "nano banana" has already ranked as the world's top image editor on the LMArena leaderboard and it's earning rave reviews from users. Nano Banana is designed to solve one of AI's biggest frustrations: consistency. By enabling precise edits, multi-turn tweaking, and seamless style mixing, Google isn't just chasing technical polish – it's gunning for its own breakout cultural moment, the kind of mass adoption that Studio Ghibli – style generations once delivered for GPT.
Adobe Firefly now supports partner AI models, moodboards, and enterprise APIs
More options, more control, more GenAI
ChatGPT nears one billion users as Ghibli-style AI images double weekly actives
ChatGPT was the world's most downloaded app in March
AI startup Midjourney plans move into the hardware market
Multiple "form factors" are being considered
16 AI "undressing" websites sued for creating deepfaked nude images
The sites were visited 200 million times during the first six months of 2024
AMD launches Amuse: a local AI image generator featuring Stable Diffusion and XDNA Super Resolution
Amuse is an AI image generator that runs locally on your PC and employs AMD XDNA Super Resolution technology to upscale images to twice the resolution compared to Stable Diffusion. It currently runs only on modern AMD hardware.
Researchers leverage astronomy tools and principles to detect deepfakes
The technique looks for inconsistencies in eyball reflections
MIT researchers showcase novel method for super-fast AI image generation
Uncannily Fast: Generative AI services can produce a high-quality visual patchwork but are usually quite sluggish. Researchers from MIT and Adobe have developed a potential solution to this time-consuming issue, with a new super-fast image generation method with minimal impact on quality. The technique spits out about 20 images per second.
Stable Diffusion 3.0 update (almost) perfects typography in generated images
Stability AI is diffusing the line between real and rendered text with this one
Photoshop's Generative Fill tool has users flooding Twitter with cool expansions of iconic album art
Some of the expansions might have made even better covers than the original
AI image generation comes to Photoshop with native Adobe Firefly integration
Smoothly add new elements to pictures with or without prompts
How to Use Midjourney to Create AI Images
AI image generators are hot news, so it takes something special to stand out in the crowd. Midjourney is among the best, read on to find out why and how to use it. We've updated our guide with new samples and a showcase of v5.1 capabilities.
Midjourney 5 improves almost every aspect of AI generated images
While it's still possible to get weird output, MJ5 vastly improves image quality
Researchers discover AI models generate photos of real people and copyrighted images
It will get worse as these systems grow in size
How to Run Stable Diffusion on Your PC to Generate AI Images
Stable Diffusion is one the newest AI image generators and is completely open-source. Learn how to use it for image creation, upscaling, and more with our detailed guide.
