GitHub 上提供 90+ 个可直接使用的 Nano Banana 提示词
- Ethan Carter

- 7月29日
- 讀畢需時 8 分鐘

AI 图像生成的效果取决于提示词的质量。一个结构良好的提示词可以彻底改变结果,帮助创作者解锁更高层次的细节、风格和创意。为此,一个 GitHub 项目汇集了 超过 90 个 Nano Banana 提示词 到一个资源库中——为艺术家、开发者和 AI 爱好者提供可直接使用的实验资源。
使用 Nano Banana 提示词的真实案例
Nano Banana 提示词库并非只是理论——它已应用于不同创意和专业领域的实际场景。以下示例展示了这些提示词如何帮助释放 AI 的潜力。
注意: 由于篇幅限制,我们在此仅展示前 30 个案例示例。完整的 90+ 个案例合集,请访问官方 Nano Banana GitHub 代码库。
案例 1:插画转手办(作者 @ZHO_ZHO_ZHO)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张参考图片,作为生成手办的对象
提示词:
turn this photo into a character figure. Behind it, place a box with the character's image printed on it, and a computer showing the Blender modeling process on its screen. In front of the box, add a round plastic base with the character figure standing on it. set the scene indoors if possible案例 2:根据地图箭头生成地面视角(作者 @tokumin)
输入 | 输出 |
![]() | ![]() |
![]() | ![]() |
![]() | ![]() |
输入: 需要上传一张包含红色箭头的 Google Maps 图片
提示词:
draw what the red arrow sees / draw the real world view from the red circle in the direction of the arrow.案例 3:现实世界 AR 信息(作者 @bilawalsidhu)
输出 |
![]() |
输入: 需要上传一张参考图片
提示词:
you are a location-based AR experience generator. highlight [point of interest] in this image and annotate relevant information about it.注意
需要在提示词中输入要标注的兴趣点 [POI]
案例 4:提取 3D 建筑/制作等距模型(作者 @Zieeett)
输入 | 输出 |
![]() | ![]() |
![]() | ![]() |
输入: 需要上传一张包含相应对象的图片
提示词:
Make Image Daytime and Isometric [Building Only]注意
根据需要修改 [方括号] 中的信息(可设置为车辆、人物等)
案例 5:不同时代的自己照片(作者 @AmirMushich)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张人物照片
提示词:
Change the characer's style to [1970]'s classical [male] style
Add [long curly] hair,
[long mustache],
change the background to the iconic [californian summer landscape]
Don't change the character's face注意
将 [方括号] 中的文字改为您的时代和详细信息
案例 6:多参考图像生成(作者 @MrDavids1)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传多张参考图片
提示词:
A model is posing and leaning against a pink bmw. She is wearing the following items, the scene is against a light grey background. The green alien is a keychain and it's attached to the pink handbag. The model also has a pink parrot on her shoulder. There is a pug sitting next to her wearing a pink collar and gold headphones.注意
提示词需要详细描述,并包含多个参考对象
输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张需要修正的图片
提示词:
This photo is very boring and plain. Enhance it! Increase the contrast, boost the colors, and improve the lighting to make it richer,You can crop and delete details that affect the composition.输入 | 输出 |
![]() | ![]() |
输入: 需要上传角色图片和手绘草图
提示词:
Have these two characters fight using the pose from Figure 3. Add appropriate visual backgrounds and scene interactions,Generated image ratio is 16:9输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张从地面拍摄的照片
提示词:
Convert the photo to a top-down view and mark the location of the photographer.输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张贴纸参考图片和一张角色图片
提示词:
Help me turn the character into a white outline sticker similar to Figure 2. The character needs to be transformed into a web illustration style, and add a playful white outline short phrase describing Figure 1.案例 11:动漫转真人 Cosplay(作者 @ZHO_ZHO_ZHO)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传一张插画图片
提示词:
Generate a photo of a girl cosplaying this illustration, with the background set at Comiket案例 12:生成角色设计(作者 @ZHO_ZHO_ZHO)
输入 | 输出 |
![]() | ![]() |
输入:需要上传一张角色参考图片
提示词:
Generate character design for me (Character Design)
Proportion design (different height comparisons, head-to-body ratio, etc.)
Three views (front, side, back)
Expression design (Expression Sheet) → like the image you sent
Pose design (Pose Sheet) → various common poses
Costume design (Costume Design)案例 13:带配色方案的彩色线稿(作者:@ZHO_ZHO_ZHO)
输入 | 输出 |
![]() | ![]() |
输入:需要上传一张线稿图片和一张配色方案图片
提示词:
Accurately use the color palette from Figure 2 to color the character in Figure 1输出 |
![]() |
输入:需要上传一篇博客/文章
提示词:
Generate an infographic for the article content
Requirements:
1. Translate the content into English and extract key information from the article
2. Keep the content in the image concise, only retaining the main title
3. Use English text in the image
4. Add rich and cute cartoon characters and elements案例 15:更换多种发型(作者:@balconychy)
输出 |
![]() |
输入:需要上传一张需要更换发型的人像图片
提示词:
Generate avatars of this person with different hairstyles in a 3x3 grid format案例 16:模型标注说明图(作者:@berryxia_ai)
输出 |
![]() |
注意
标注结果中存在相当数量的错误 ⚠️。请注意,Nano-Banana 的标注并非完全准确,使用前请仔细核实信息的正确性。
提示词:
Draw [3D human organ model display example heart] for academic presentation, with annotations and explanations, suitable for showcasing its principles and [each organ's] functions, very realistic, highly detailed, with extremely fine design.注
将 [括号] 中的文本替换为您想要展示的模型
输出 |
![]() |
输入:需要上传一张参考图片
提示词:
A photorealistic image of an ultra-detailed sculpture of the subject in image made of shining marble. The sculpture should display smooth and reflective marble surface, emphasizing its luster and artistic craftsmanship. The design is elegant, highlighting the beauty and depth of marble. The lighting in the image should enhance the sculpture's contours and textures, creating a visually stunning and mesmerizing effect输入 | 输出 |
![]() | ![]() |
![]() | ![]() |
![]() | ![]() |
输入:需要上传一张包含各种食材的照片
提示词:
make me a delicious lunch with these ingredients, and put it on a plate , zoomed in view of the plate, remove the other plates and ingredients.案例 19:数学题推理(作者:@Gorden Sun)
输入 | 输出 |
![]() | ![]() |
输入:需要上传一道数学题
提示词:
Write the answer to the problem in the corresponding position based on the question案例 20:老照片上色(作者:@GeminiApp)
输入 | 输出 |
![]() | ![]() |
输入:需要上传一张需要修复的老照片
提示词:
restore and colorize this photo.输入 | 输出 |
![]() | ![]() |
输入:需要上传一张人物图片和一张服装图片
提示词:
Choose the person in Image 1 and dress them in all the clothing and accessories from Image 2. Shoot a series of realistic OOTD-style photos outdoors, using natural lighting, a stylish street style, and clear full-body shots. Keep the person's identity and pose from Image 1, but show the complete outfit and accessories from Image 2 in a cohesive, stylish way.输入 | 输出 |
![]() | ![]() |
输入:需要上传人物图片和服装图片
提示词:
Replace the person's clothing in the input image with the target clothing shown in the reference image. Keep the person's pose, facial expression, background, and overall realism unchanged. Make the new outfit look natural, well-fitted, and consistent with lighting and shadows. Do not alter the person's identity or the environment — only change the clothes.案例 23:多视角结果生成(作者:@Error_HTTP_404)
输入 | 输出 |
![]() | ![]() |
输入:需要上传参考图片
提示词:
Generate the Front, Rear, Left, Right, Top, Bottom views on white. Evenly spaced. Consistent subject. Isometric Perspective Equivalence. 案例 24:电影分镜(作者:@GeminiApp)
输入 | 输出 |
![]() | ![]() |
输入:需要上传参考图片
提示词:
Create an addictively intriguing 12 part story with 12 images with these two characters in a classic black and white film noir detective story. Make it about missing treasure that they get clues for throughout and then finally discover. The story is thrilling throughout with emotional highs and lows and ending on a great twist and high note. Do not include any words or text on the images but tell the story purely through the imagery itself.案例 25:角色姿势修改(作者:@arrakis_ai)
输入 | 输出 |
![]() | ![]() |
输入:需要上传参考图片
提示词:
Have the person in the picture look straight ahead案例 26:根据线稿生成图片(作者:@ZHO_ZHO_ZHO)
输入 | 输出 |
![]() | ![]() |
输入:需要上传线稿和参考图片
提示词:
Change the pose of the person in Figure 1 to that of Figure 2, and shoot in a professional studio案例 27:为图片添加水印(作者:@AiMachete)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传参考图片
提示词:
Watermark the word ‘TRUMP’ over and over again across the whole image.案例 28:知识推理图像生成(作者:@icreatelife)
输出 |
![]() |
![]() |
提示词:
Make me an infographic of 5 tallest buildings in the world / Make a colorful infographic of the sweetest things on Earth案例 29:红笔批注(作者:@AiMachete)
输入 | 输出 |
![]() | ![]() |
输入: 需要上传参考图片
提示词:
Analyze this image. Use red pen to denote where you can improve.案例 30:爆炸美食(作者:@icreatelife)
输出 |
![]() |
![]() |
输入: 需要上传参考图片
提示词:
Photograph this product in a dramatic modern scene accompanied by explosive outward dynamic arrangement of the key ingredients fresh and raw flying around the product signifying its freshness and nutritional value. promo ad shot, without text, product is emphasized, with the key brand colors as background.使用 remio 自动保存提示词

remio 让捕获、整理和检索提示词变得简单,它将自动抓取与其大型语言模型(LLM)相结合。此功能可确保您最有价值的提示词永不丢失,并可在各个项目中无缝复用。
以下是使用 Remio 将提示词保存到您的资料库的方法:
使用 Google Chrome 扩展程序 并点击“添加到收藏集”,即可将提示词直接保存到所需的收藏集中。
前往 remio 主界面 并使用@ 功能 提及特定收藏集的名称。
remio 的 LLM 随后将搜索该收藏集中存储的文档,并让您只需用自然语言提问即可检索到正确的提示词。
按照这些步骤操作后,提示词会自动存储在您的个人提示词库中,让您能够在需要时轻松管理、整理和复用它们。
结论
GitHub 上的Nano Banana 提示词库 提供了包含 90 多条精心设计的提示词这一强大资源,帮助用户探索创意、技术和以生产力为重点的使用场景。虽然本文仅重点介绍了前 30 个案例,但完整合集可直接在 GitHub 上获取,供希望深入了解的读者使用。
通过将此资料库与remio 的自动提示词保存工作流 相结合,用户可以构建一个个性化的提示词库,并使其随着时间推移自然增长。无论是通过 Chrome 扩展程序还是应用内的 @collections 功能,Remio 都能确保提示词不仅被保存,而且可在需要时被智能检索。
简而言之,Nano Banana 资料库为您提供灵感,而 Remio 让它切实可行——二者结合,助您全面提升提示词工程之旅。



































































