한국어EN
MultimodalGoogle

Gemini 2.5 Flash Image (nano-banana)

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Gemini 2.5 Flash Image (nano-banana)

Why it matters

Character-consistent editing reaches mass-market product quality; carries an invisible SynthID watermark

Source — Primary sources first; secondary reports are labelled “Press”

Officialdevelopers.googleblog.comhttps://developers.googleblog.com/en/introducing-gemini-2-5-flash-image/

Added in Week 35, 2026 · See that week

On the map — ⑦ Multimodal line

  1. Previous stopGoogle DeepMind
  2. This recordGemini 2.5 Flash Image
  3. Next stopDeepSeek-OCR
See it on the map

In the model family tree — Gemini family · 21 versions

  1. Earlier versionGemini Robotics / Robotics-ER
  2. This recordGemini 2.5 Flash Image (nano-banana)
  3. Later versionGemini Robotics 1.5 / ER 1.5
See the whole Gemini family

Same week

xAI releases grok-code-fast-1OfficialOn the Theoretical Limitations of Embedding-Based Retrieval publishedPaperAnthropic and OpenAI publish a mutual alignment evaluation pilotOfficialUN General Assembly adopts resolution A/RES/79/325 by consensusGovernment

Nearby on the same axis

Genie 3OfficialOpenAI launches Sora 2 and a social appOfficialSora 2 swaps copyright opt-out for rightsholder opt-in with granular controlsOfficialSora 2 tightens deepfake guardrails on likeness rightsPress