Almanac
model

Nano Banana 2

modelactivenano-banana-2-8d882c85·4 events·first seen 28d ago

Aliases: Nano Banana 2, Nano Banana, Nano-banana 2

Co-occurring entities

More like this (12)

Recent events (4)

6Google Deepmind Blog·28d ago·source ↗

Nano Banana 2: Combining Pro capabilities with lightning-fast speed

DeepMind has announced Nano Banana 2, a new image generation model described as combining Pro-level capabilities with Flash-level inference speed. The model is positioned as production-ready, featuring advanced world knowledge, subject consistency, and fast generation. The announcement appears to target developers and enterprise users seeking high-quality image generation at lower latency.

5The Batch·13d ago·source ↗

DeepLearning.AI launches Context Hub for coding agents; Google releases Nano Banana 2 image generator

Andrew Ng and collaborators released Context Hub (chub), an open CLI tool that provides coding agents with up-to-date API documentation to reduce hallucinated or outdated API calls. Google separately launched Nano Banana 2 (Gemini 3.1 Flash Image), a faster and cheaper image-generation system built on Gemini 3 Flash's mixture-of-experts architecture, priced at roughly half its predecessor and claiming the top spot on Arena.ai's text-to-image leaderboard. The newsletter also references Claude Opus 4.6 as a leading coding model and notes the growth of agent-to-agent social infrastructure (OpenClaw, Moltbook) as context for the tooling need.

6The Batch·15d ago·source ↗

Google Debuted Lyria 3, An App That Turns Text or Images Into 30-Second Songs

Google launched Lyria 3, a latent diffusion-based music generation model integrated into the Gemini app and YouTube Shorts, capable of producing 30-second audio clips with vocals and instruments from text or image prompts. Unlike its predecessor Lyria 2, Lyria 3 was trained on licensed audio data and includes copyright-filtering safeguards, SynthID watermarking, and RLHF fine-tuning. The model is available free to Gemini users (18+) and YouTube Shorts creators, reaching an estimated 750 million users. Google also acquired ProducerAI (formerly Riffusion) shortly after launch, signaling continued investment in AI music tooling.

5arXiv · cs.CL·9d ago·source ↗

MMAE: First comprehensive benchmark for instruction-based audio editing across 7 modalities

Researchers introduce MMAE, a 2,000-sample benchmark for evaluating general-purpose instruction-based audio editing systems, covering 7 audio modalities (sound, speech, music, and mixtures) and 6 levels of task complexity. The benchmark uses a rubric-based evaluation framework decomposing tasks into 17,741 verifiable criteria to assess instruction following and context consistency. Evaluation of leading models reveals severe limitations: Exact Match Rate falls below 5% overall and hits 0% on complex mixed-modality tasks, exposing fundamental gaps in current audio editing systems.