Nano Banana 2: Google’s latest AI image generation model

kept by eddie feb 27

Google DeepMind launches Nano Banana 2, combining advanced image generation features with Gemini Flash's speed for rapid editing and iteration.

Gemini 3.1 Flash TTS: New text-to-speech AI model
Gemini 3.1 Flash TTS introduces audio tags for granular control over vocal style and pacing in over 70 languages, delivering top-quality, watermarked speech generation.
also on Vertex AI, SynthID, #generative-ai, #ai, #developer-tools
AI image generators are getting better by getting worse
AI image generators improve realism by mimicking the imperfections of phone camera photos, making fakes harder to detect.
also on C2PA, Gemini, #generative-ai
DuckDuckGo rolls out AI-powered image editing on Duck.ai - 9to5Mac
DuckDuckGo adds free, private AI image editing to Duck.ai, using OpenAI models while stripping user metadata and storing uploads locally.
also on C2PA, #ai-integration
Nano Banana Pro
Hacker News commenters critique Google's Nano Banana Pro image model for vague rollout, SynthID watermark removability, and unreliable text and diagram generation.
also on SynthID, Gemini, #generative-ai, #ai, #developer-tools
Nano Banana Pro aka gemini-3-pro-image-preview is the best available image generation model
Nano Banana Pro delivers best-in-class image generation with precise instruction following, legible text rendering, and SynthID watermarking.
also on SynthID, #generative-ai, #ai, #developer-tools