Fast drafts, fast finals
Draft at 1K in seconds, then ship the winner at 2K or 4K. Ideas stop waiting on renders.
Nano Banana 2.1 is live — sharper edits, cleaner text, up to 4K
Text to Video AI
Write the shot — subject, action, camera move, mood — and watch it render with synchronized sound.
AI 模型 5 點數
提示詞0/2000
請避免使用受版權保護的角色、標誌、音樂及敏感或違規內容，否則可能被攔截。
解析度
長寬比
批量生成1
預估費用：5 點數
你的作品將顯示在此
選擇模型、描述鏡頭，然後點擊生成。
Why Nano Banana AI
One model. Every visual you described.
The Nano Banana 2.1 model reads prompts like an art director — subject, composition, light, and typography — and renders images that look finished, not synthesized.
Multi-reference editing
Feed up to eight reference images — subjects, styles, and scenes stay consistent while you change exactly what you asked.
Readable text rendering
Posters, packaging, and signage come out with crisp, legible type — one of the strongest text-in-image models available.
Beyond images
The same studio hosts frontier video models — Muse Video, Seedance 2.5, MiniMax H3 — for when your still needs to move.
How it works
From sentence to visual in three steps
Write what you want to see — subject, style, lighting, mood. Drop reference images if you have them.
00:0000:1500:30
Made for
Built for people who ship visuals
Creators & studios
Concept art, storyboards, thumbnails, and key visuals — without waiting on a render farm or a reshoot.
Marketers
Turn product shots and copy into scroll-stopping creatives for every placement and ratio.
E-commerce teams
Reshoot catalog photos in new scenes, swap backgrounds, and produce seasonal variants on demand.
Designers
Posters, mockups, and text-accurate layouts — iterate in natural language instead of rebuilding layers.
Capabilities
Every frontier model in one studio
Switch engines without switching tools — Nano Banana 2.1 plus the strongest public image and video models, side by side in the Nano Banana AI studio.
Multi-reference editingCharacter consistencyText rendering1K–4K outputConversational editsStyle transferVideo generationBatch runs
Muse VideoNew原生音訊旗艦多模態影片
Seedance 2.5Hot多參考 Seedance（原生音訊）Seedance 2.0上一代 Seedance（最高 1080p）Seedance 2.0 FastFast最快的 Seedance（草稿用）
MiniMax H3快速文字/圖像轉影片，最高 2KMiniMax H3 MaxHot參考驅動的影片一致性
Veo 3.1Google 電影感打稿引擎
Wan 3.0彈性時長與自適應取景
Kling 3.0一句提示詞生成戲劇性動態
GPT Image 2.5New銳利文字與精準編輯，最高 4KGPT Image 2萬用圖像生成，最高 4KNano Banana 2.1New快速草稿與精準編修，最高 4KNano Banana ProHot4K 高保真圖像輸出Nano Banana 2快速草稿與對話式編輯Nano Banana 2 LiteFast快速、低成本草稿的輕量版FAQ
Questions, answered
How do I write a good video prompt?
Lead with the subject and action, then add camera language ("slow push-in", "aerial orbit") and lighting mood. Our prompt guide has templates.
How long can a text-to-video clip be?
Muse Video generates up to 30 seconds per run; most models sit in the 4–15 second range.
Can I generate without a prompt?
Reference mode lets stills drive the generation, but a short prompt always improves control.
Which model should I start with?
Muse Video — it handles the widest prompt range and adds native audio.