NANO BANANA 2.1 图像模型

Nano Banana 2.1 AI 图片生成器

Nano Banana 2.1(Gemini Nano Banana 2.1)是 Google 从 Nano Banana 2 更新而来的图像生成与对话式编辑模型。可用于带文字的设计、多参考图组合,或按文字创意生成新场景。

nano2.1
NANO BANANA 2.1 案例

Nano Banana 2.1 图片案例

分别查看人物写真、商品静物和室内场景。结合结果阅读完整原始提示词;室内编辑案例还提供原始参考照片。

月球温室人物写真

月球温室人物写真

将植物学家宇航员放在左侧,蓝色发光蕨类放在右侧。描述光线与玻璃温室环境,生成后检查面部和手部。

Create a finished 4:5 environmental portrait of one botanist-astronaut cataloging a luminous blue fern inside a lunar greenhouse at night. The person stands in the left third, seen from knees up, wearing a practical white exploration suit with a clear helmet held under one arm. The fern is the sharp foreground subject on the right, while curved glass walls reveal the gray lunar surface and a small Earth low on the horizon. Shoot at eye level with a 50mm lens and moderate depth of field. Use cool moonlight from the right, soft amber work lights from the left, realistic skin and fabric texture, restrained blue-and-amber color grading, and a quiet documentary mood. No extra people, no flags, no readable labels, no fantasy magic particles, no logos, no watermark.
使用此提示词
ORBIT TEA 商品海报

ORBIT TEA 商品海报

指定一个饮料罐、准确标题与说明文字、水果和石质底座,检查文字、商品形状和摆放位置。

Create a premium vertical ecommerce launch poster for a fictional sparkling tea brand. Hero product: one slim matte-white aluminum can with a simple navy crescent symbol, realistic condensation, peach slices and yuzu peel, on a pale stone pedestal. Warm peach-to-cream gradient background, soft studio shadows, refined editorial layout, photoreal product lighting, generous negative space. Render exactly these five text lines, spelled exactly as written: ORBIT TEA; PEACH + YUZU; SPARKLING TEA; ZERO ADDED SUGAR; SHOP THE DROP. Keep ORBIT TEA as the largest headline, PEACH + YUZU directly below it, SPARKLING TEA and ZERO ADDED SUGAR as small but clearly legible supporting lines, and SHOP THE DROP as a compact button-style callout. Do not add, duplicate, alter, or misspell any text. No people, no hands, no extra cans, no third-party logos, no watermark.
使用此提示词
日光下的日式北欧客厅
原始房间

日光下的日式北欧客厅

以原始房间作为建筑参考,调整表面材质与家具。对照输入检查窗户、门洞、暖气片和透视。

Use the reference photo as a locked architectural plate and perform a finish-and-furniture edit only. Preserve the exact pixel-aligned camera view, perspective, room dimensions, ceiling, all wall edges, the single tall black-framed window on the left with the same opening and frame pattern, the white radiator directly below it, and the centered back doorway with the same size and position. Do not alter, repaint, subdivide, widen, narrow, shift, add, or remove any architectural opening or fixed fixture. Change only: beige tile to pale natural oak flooring; walls to warm off-white plaster; add a low oatmeal linen sofa fully along the right wall, a slim oval oak coffee table on a cream textured rug, one minimal black reading lamp, and one olive tree in a clay pot at back right. Soft natural late-morning light, photorealistic Japandi interior photography, uncluttered. No new windows, no extra doors, no window mullions, no curtains covering the frame, no camera movement, no lens change.
使用此提示词
认识 NANO BANANA 2.1

Nano Banana 2.1 是什么,适合做什么?

Nano Banana 2.1 对应 Google 的 gemini-nano-banana-2.1,是 Nano Banana 2 的更新。Google 介绍了文字渲染、信息图布局和角色一致性的改进。在 WeShop,可用文字或参考图片制作商品海报、流程图、人像和场景编辑;使用结果前请检查文字、面部及细节。

文字与信息图布局

指定一个饮料罐、准确标题与说明文字、水果和石质底座,检查文字、商品形状和摆放位置。

参考图引导的场景编辑

以原始房间作为建筑参考,调整表面材质与家具。对照输入检查窗户、门洞、暖气片和透视。

清楚的角色识别特征

用服装、颜色和配饰指导角色连续性。六格分镜重复使用小熊猫、云朵精灵和黄铜机械鸟;请逐格检查角色是否缺失、外观是否变化。

创作模式

选择起始输入

新图片可以从文字开始,编辑或合成时添加参考照片。描述主体、构图与所需变化;有多张参考时,为每个上传文件分配明确职责。

从参考照片开始

上传用于编辑的主体或场景。如果有多份输入,请说明各参考素材的用途和需要的修改。

从文字描述创作

描述新的主体、场景、构图与视觉表现,并写明需要出现在图像里的文字。

提示词指南

Nano Banana 2.1 提示词怎么写?

结合输入与结果,学习完整原始提示词中的参考职责、保留指令、文字层级、构图与光线,再改用于自己的素材。

WeShop 结果:小熊猫、云朵角色与机械鸟……
参考素材 1

在分镜格间延续角色特征

点名每个角色的颜色与配饰,再按顺序描述六格画面。角色设定参考图指导重复出场的角色;请逐格检查人物、服装和配饰。

Use the uploaded lineup as the exact character reference. Create one polished 3-by-2 storyboard sheet with six equal cinematic panels, read left to right and top to bottom, in the same hand-painted storybook animation style. Preserve the identity, proportions, colors, clothing, and accessories of all three characters in every panel: Rhea is the red panda courier with teal hooded cape, tan satchel, and brass compass; Nimbus is the pale-blue cloud spirit with yellow scarf and star hair clip; Tock is the brass bird robot with cobalt-blue eye and winding key. Story: the trio delivers a glowing letter to a floating sky library. Panel 1: they arrive at the edge of a broken rope bridge above clouds. Panel 2: Rhea studies the compass while Nimbus points toward the distant library and Tock watches. Panel 3: the bridge collapses and all three react with surprise. Panel 4: Nimbus expands into a soft cloud platform carrying Rhea and Tock across the gap. Panel 5: they land at the sky library doors and Rhea holds up the glowing letter. Panel 6: inside the warm library, the three friends celebrate together as the delivered letter becomes a small constellation overhead. Keep exactly one Rhea, one Nimbus, and one Tock in every panel. Vary camera distance and poses, but keep faces, costume colors, body shapes, and signature accessories consistent. Clear white gutters between panels. No speech bubbles, no captions, no text, no logos, no watermark, no extra characters.
WeShop 结果:老妇坐在木质门廊上,身旁是……
参考素材 1

区分照片修复与人物改动

将需要修复的破损与要保留的脸、姿态和构图区分开。此例修复一张合成的年代风格照片,并添加柔和颜色;保留原图,生成颜色属于创作性解释。

Restore this damaged 1948 black-and-white family photograph while preserving the exact identities, ages, facial proportions, poses, clothing, porch architecture, framing, and historical period. Repair the lower-left tear, remove scratches and dust, recover balanced contrast and fine facial detail, and add restrained historically plausible natural color: weathered gray porch boards, muted cream and brown clothing, natural skin tones, and subdued green countryside. Do not beautify faces, change expressions, invent jewelry, alter clothing, add people, remove people, crop, modernize, add text, logo, or watermark. Keep subtle film grain so it remains an archival photograph rather than a modern digital portrait.
WeShop 结果:窗户亮灯的现代住宅周围……
参考素材 1

保留场景,改变光线

指定光线与时间变化,并写清需要保留的建筑细节。对照日间参考图检查窗户、屋顶线、泳池边缘与取景。

Edit only the lighting and time of day in the uploaded architectural render. Change the soft overcast daylight to calm blue hour just after sunset, with a deep blue sky, warm 3000K interior light visible through the existing windows, and subtle warm reflections on the existing pool. Preserve the camera, crop, lens perspective, house massing, flat roof, skylight, every window and door opening, recessed entrance, balcony, wall edges, pool footprint, paving, materials, planting, and all object positions exactly. Do not add, remove, move, resize, duplicate, or redesign any architectural element. No people, furniture, vehicles, text, logo, or watermark.
写清剖面空间与物件位置

写清剖面空间与物件位置

写清一个方形剖面房间、两面后墙、书架,以及独立的阅读和桌椅区域。微缩图书馆结合温润木材、绿色软装与柔和光线。

Create one isometric cutaway illustration of a tiny neighborhood library as a handcrafted miniature diorama. Orthographic view from above at a 30-degree angle, parallel verticals, no wide-angle distortion. Remove the roof and both front-facing walls so the interior is completely visible; retain the two rear walls. One single square room on a thick square base. An L-shaped wall of walnut bookshelves follows the two rear walls; a forest-green reading armchair and brass floor lamp sit on the left; one round oak table with two stools sits on the right; a small arched window is centered on the back wall. Leave a clear walking path through the middle. Warm ivory plaster, walnut wood, green upholstery, terracotta accents, tiny books with blank spines, soft clay-like materials and fine paper texture. Soft afternoon light from upper left, gentle ambient occlusion, clean warm off-white background, whole base visible with generous breathing room. Cozy editorial illustration, precise readable shapes. No people, no letters, no labels, no watermark, no extra rooms, no exterior street.
用暖色车窗对比冷色风景

用暖色车窗对比冷色风景

将一列玻璃图书馆列车置于云海之上,让温暖车窗与蓝色黎明形成对照,并写清列车、弯月与远山的位置。

Create a finished 16:9 cinematic editorial image of exactly one glass-walled library train traveling from left to right on a narrow elevated rail above a sea of clouds. Show the entire train in the middle third of the frame, with a small reading lounge visible through warm amber windows. Place a pale crescent moon in the upper-left and distant blue mountains in the lower-right. Use a wide 35mm view, eye-level horizon, generous negative space, cool blue dawn light outside, warm tungsten light inside, realistic atmospheric depth, and subtle film grain. No people outside the train, no floating books, no extra vehicles, no text, logos, or watermark.
WeShop 结果:风暴后的灯塔

把光线与色彩放入具体场景

一起描述光线方向、天气、配色和取景。灯塔提示词要求雨后金色阳光、青绿色海水,以及通向灯塔的小路。

A solitary white lighthouse on a rugged green headland above a deep teal sea just after a storm. A winding stone path leads from the bottom foreground to the lighthouse in the upper third. Golden sunlight breaks through layered clouds, waves foam against dark rocks. Photorealistic landscape photography, vertical 3:4 composition, no people, no lettering, no border or watermark.
使用方法

创建第一张 Nano Banana 2.1 图片

在本页顶部生成器准备输入、核对请求,再检查生成图片。

  1. 提供此模型所需的输入

    撰写新图创意,或添加需要编辑、组合的照片。按上传顺序标识参考,说明要保留什么、改变什么。

  2. 检查可用设置与积分

    核对可选的 1K、2K、4K 尺寸设置、画幅比例和结果数量。生成前检查积分预估及账户模型权限。

  3. 打开并检查结果

    将结果与创意及参考图对照。校对文字、检查脸和手,并逐格检查分镜。下载原始文件核对实际像素尺寸。

Nano Banana 2.1 教程

探索八篇实用教程,学习参考图、局部编辑、商品摄影、分镜、信息图、照片修复及建筑场景创作。

模型选择

哪个 Nano 版本适合你的任务?

原版 Nano Banana 适用于图像创作与参考图编辑,Pro 侧重细致设计和创作控制,Nano Banana 2 面向高效的 Flash 图像创作,2.1 则改进了文字、布局和视觉连贯性。可结合下表的输入与输出选项选择版本。

比较维度Nano BananaNano Banana ProNano Banana 2Nano Banana 2.1
模型定位原版 Gemini 2.5 Flash Image 图像创作与编辑Gemini 3 Pro Image,侧重细致设计与创作控制Gemini 3.1 Flash Image,侧重高效创作与编辑Nano Banana 2.1 更新,侧重版式与视觉连续性
页面列出的输入从参考照片开始;从文字描述创作创作新设计;使用参考主体从参考照片开始;从文字描述创作从参考照片开始;从文字描述创作
WeShop 当前选项宽高比:auto、1:1、2:3、3:2、4:3、3:4、4:5、5:4、16:9、9:16、21:9图像尺寸选项:1K、2K、4K图像尺寸选项:1K、2K、4K图像尺寸选项:1K、2K、4K
模型定位
Nano Banana
原版 Gemini 2.5 Flash Image 图像创作与编辑
Nano Banana Pro
Gemini 3 Pro Image,侧重细致设计与创作控制
Nano Banana 2
Gemini 3.1 Flash Image,侧重高效创作与编辑
Nano Banana 2.1
Nano Banana 2.1 更新,侧重版式与视觉连续性
页面列出的输入
Nano Banana
从参考照片开始;从文字描述创作
Nano Banana Pro
创作新设计;使用参考主体
Nano Banana 2
从参考照片开始;从文字描述创作
Nano Banana 2.1
从参考照片开始;从文字描述创作
WeShop 当前选项
Nano Banana
宽高比:auto、1:1、2:3、3:2、4:3、3:4、4:5、5:4、16:9、9:16、21:9
Nano Banana Pro
图像尺寸选项:1K、2K、4K
Nano Banana 2
图像尺寸选项:1K、2K、4K
Nano Banana 2.1
图像尺寸选项:1K、2K、4K

选择 Nano Banana

使用原版 Gemini 2.5 Flash Image,根据文字描述创作图像或改绘参考图片。

选择 Nano Banana

选择 Nano Banana Pro

选择 Nano Banana 2

需要高效的图像创作与参考图编辑时,可考虑 Gemini 3.1 Flash Image。

选择 Nano Banana 2

选择 Nano Banana 2.1

需要文字较多的布局和视觉连贯性时,可考虑 Nano Banana 2 的这一更新版本。

选择 Nano Banana 2.1
更多图像模型

更多图像编辑模型

探索其他图像编辑模型,比较参考图、提示词与可用设置。

常见问题

Nano Banana 2.1 常见问题

关于此版本、输入要求与开始使用的常见问题。

Nano Banana 2.1 是什么?

Nano Banana 2.1 是 Google 的 Gemini Nano Banana 2.1 模型,代码为 gemini-nano-banana-2.1,是 Nano Banana 2 的图像生成与对话式编辑更新。Google 介绍了文字渲染、信息图布局及角色一致性的改进。

它适合做什么?

适合带文字的海报、流程信息图、参考图人像、场景编辑与插画分镜。本页案例提供完整提示词、输入参考及单次生成结果。

不上传照片可以生成吗?

可以。用文字描述主体、场景、构图和风格;需要文字时,提供准确文案与位置。需要编辑或组合现有视觉素材时,再上传参考图。

多张参考图应该怎么使用?

写明每张图提供人物、服装、商品还是环境,并让提示词中的角色与实际上传顺序对应。生成后对照参考检查面部、服装及物件细节。

可以选择哪些尺寸和画幅?

WeShop 提供 1K、2K、4K 尺寸设置。画幅比例为 auto、1:1、2:3、3:2、4:3、3:4、4:5、5:4、16:9、9:16、21:9、1:4、4:1、1:8、8:1。这些是请求设置,文件实际像素尺寸与格式以下载结果为准。

Nano Banana 2.1 提示词怎么写?

描述主体与场景、构图、风格和光线。编辑时写清改变什么、保留什么;使用参考图时标明各图职责;海报或信息图需给出准确文字与阅读顺序。可从本页完整配对案例开始改写。

2.1、2 和 Pro 怎么选?

需要新版文字布局与参考图创作时可用 2.1。Nano Banana 2 是独立的 Gemini 3.1 Flash Image 选项,可继续既有版本流程。Google 将 Pro、Gemini 3 Pro Image 定位于复杂视觉任务与专业素材。请结合各页案例及可用设置选择。

如何查看使用权限和费用?

在 WeShop 定价页及账户中查看模型权限和可用积分,提交前核对生成器按所选设置与数量显示的积分预估。

生成后应检查什么?

校对文字和小标签,对照参考检查脸与服装,并查看手部、物件数量及场景几何。分镜需逐格检查角色和顺序。即使提示词要求保留,参考编辑仍可能改变细节。