Google ships Nano Banana 2.1: 4K photoreal output, better Chinese text, 1K/2K pricing cut in half
量子位 · wechat · 2026-10-10
Google quietly released Nano Banana 2.1, a new image generation model upgrading visual design, mask editing, subject consistency and realism.
- Benchmarks: On Arena it averages +61.7 points over Nano Banana 2 across three tasks; text-to-image ranks 4th (+80, behind only GPT), multi-image editing 5th (1328), single-image editing 6th (1428).
- Highlights: Photoreal 4K output, much cleaner Chinese text rendering, and a full image-to-video workflow via Veo 3.1 in Google Flow.
- Caveats: Reviewers find overall completeness still behind GPT Image 2.5, and a watermark bug degrades quality over repeated edits.
- Pricing: 1K/2K generation halved, 4K down 25%. Live in Gemini App and AI Studio (50 free credits/day); API via gemini-nano-banana-2.1.
More from Multimodal
- One prompt turned OpenAI's 722 math papers into a 92-second animated explainer via Opus — FinanceYF5 · 2026-10-10
- Dev recreates fictional ChatGPT UIs for Windows 98, XP, Vista and 7 — Midnight_Sun_BR · 2026-10-10
- MiniMax H3 removes people from videos inside ComfyUI — RobbaW · 2026-10-10
- BudgetPix: Google and UIUC's pixel diffusion model adapts compute per image, cutting tokens to 10% — CSProfKGD · 2026-10-10
- Free Female Face Prompt Builder adds natural-language-to-SD prompt conversion — dobelmont · 2026-10-10
- Model tuning could stop AI video from fighting 2D animation style, says Andrew Carr — andrew_n_carr · 2026-10-10