年度会员优惠升级年度会员 · 享 5 折优惠
查看套餐
Nano Banana Pro
首页首页
Nano Banana Series
Nano Banana Pro
RECOMMENDED

根据文本描述生成高质量图像

Nano Banana 2

新一代 · Google 搜索 · 14张输入图

Nano Banana 2 Lite

Nano Banana 2 的轻量快速版

GPT Image Series
GPT Image 2.5
RECOMMENDED

自然光影 · 丰富质感 · 精细细节呈现

GPT Image 2

照片级真实感 · 精准文本渲染 · 像素级编辑

GPT Image 1.5

搭载最新 GPT 5.2 技术的图像生成

Seedream SeriesRELAXED
Seedream 5 Pro
NEW

效果比肩 Nano Banana 2,精准编辑,图层自由

Seedream 5 Lite

最新 Seedream 模型,4K 画质,8 种宽高比

Seedream 4.0

4K分辨率支持,宽松的内容政策,批量生成功能

Qwen Image
Qwen Image 3.0

复杂图文排版 · 清晰文字渲染 · 细腻写实

Creative Tools
图像增强

提升图像分辨率,优化细节表现

电商套图

上传产品图,生成主流商城完整套图

Nano Banana Pro 抽卡

一次生成多张卡片网格图

GPT Image 2 抽卡

基于 GPT Image 2 一次生成多张卡片网格图

Z-Image
Z-图像

快速生成逼真图像,内容限制宽松

Seedance Series
Seedance 2.5
NEW

30 秒 4K 视频生成,支持原生音频与高级控制

Seedance 2
HOT

影院级视频,原生音频,最长15秒,文生视频/图生视频

Seedance 2 Mini
HOT

高性价比 Seedance 2,原生音频,4-15秒,720p/1080p

Seedance 1.5 Pro

支持首尾帧、文生视频/图生视频模式,性价比高

Kling Series
Kling 3
HOT

原生音频支持的电影级4K生成

Kling o3

全能模型,支持首尾帧控制

Kling 2.6

电影级画质,原生音频生成

Wan Series
Wan 3.0
NEW

标准与高速 Prime 同一工作台

Wan 2.7
HOT

文生、图生、参考生成和视频编辑模式

Wan 2.6

宽松内容政策

Wan 2.5

较为宽松的内容政策,保持高创作自由度

Google Series
Gemini Omni

多模态输入 × 原生音频,电影级可控视频生成

Veo 3.1

支持首尾帧视频、多图像参考视频生成

Grok Series
Grok Imagine 1.5

xAI Grok 图生视频,支持多种比例,最长15秒

Grok

生成速度更快,提示词遵循度较弱,支持辣味模式

Hailuo AI Series
H3 Max / Turbo

高性价比的 MiniMax H3 Max 视频工作台,支持文生视频、图生视频、多模态参考生成与原生音频。

MiniMax H3(Hailuo 03)

Hailuo 03:支持文本、首尾帧和多模态参考视频

海螺AI

MiniMax Hailuo视频:支持文字/图像生成视频,首尾帧效果出众。

OmniHuman 1.5
OmniHuman 1.5

单张图片加音频生成数字人视频

V2V Lip Sync

用目标音频同步现有视频口型

AI聊天
AI Audio
NEW

Generate dialogue, ambience, sound effects, and background music

AI音乐
NEW

创作具有自定义歌词和风格的原创歌曲

创作记录创作记录
定价定价
提示词库

探索和发现高质量的 AI 提示词

Nano Banana 提示词案例

探索 Nano Banana Pro 的高质量提示词案例

GPT Image 2 提示词案例
NEW

浏览适合社交帖子、海报、商品视觉等场景的 GPT Image 2 提示词

Seedance 2.0 视频提示词案例

浏览精选 Seedance 2.0 视频案例,包含视频、作者、发布时间和互动数据。

提示词构建

提示词构建工具与指南

AI 图片提示词构建器
NEW

通过可视化界面轻松构建复杂的提示词

Seedance 2 提示词指南

深入了解高级功能和最佳实践

API
NEW

将 Nano Banana Pro 的能力集成到您的应用中

Nano Banana Pro
AI ImageAI Video

Nano Banana Pro

Nano Banana Pro 是革命性的 AI 驱动图像生成和编辑平台,提供一致的角色编辑和场景保持,性能卓越。

Email: support@nanobananapro.site

  • 邮箱

产品

  • 首页
  • 功能特点
  • 案例展示
  • 电商
  • 定价

其他服务

  • AI 图像增强器
  • Grok
  • Veo3.1
  • Wan2.5
  • Kling 4.0

其他

  • 博客
  • 关于我们
  • 除碳计划

© 2026 bananapro.site. 保留所有权利。

  • 隐私政策
  • 服务条款
  • 退款政策
  • Referral Program
  • Invoice Management
🇺🇸 English🇨🇳 中文🇰🇷 한국어🇯🇵 日本語🇪🇸 Español🇩🇪 Deutsch🇫🇷 Français🇷🇺 Русский🇸🇦 العربية🇧🇷 Português🇮🇹 Italiano
定价创作
返回 GPT Image 2 提示词
首页GPT Image 2 提示词详细的多语言中文漫画提示
漫画 / 分镜信息图 / 教育视觉动漫 / 漫画漫画 / 图像小说角色文字 / 排版城市景观 / 街景

详细的多语言中文漫画提示

详细的多语言中文漫画提示 preview image 1

A very complex prompt for generating a full-page manga featuring specific characters, vertical layouts, and precise multilingual text rendering in Chinese and English.

发布于 2026年4月22日原始语言:EN

提示词

完整提示词,可直接复制或调整。

Generate a full color Chinese-text manga about this OpenAI researcher, Chen Boyuan (first picture), who works on improving the text rendering capability of ChatGPT Image 2 model for the upcoming release. (in the background there is boba tea and a banana taped to the wall with a single slice of duct tape). The model can render insanely small Chinese text when he tried generating some detailed and beautiful multilingual infographics handdrawn-style poster about his hometown, Wuxi on his computer screen. His hard work pays off and the team was impressed by the absurdly good quality of multilingual text performance of his model, seeing all the languages it can write. When he takes a break with one hand holding his phone, he received a translated text message from Sam Altman on his phone (avatar attached as second picture), asking him to take a look at the rendered multilingual text in an image he just generated to congrat the team, since Sam only knows English. However, make it funny by let Boyuan outrage (typical manga style) at the end by seeing Sam's generated image contains a "稳稳地接住你" phrase at the central location in an otherwise perfectly rendered image that's used to congrat the team, because this sentence has been memed as an unnatural but funny Chinese sentence GPT likes to use on Chinese internet. Boyuan should rage "God! It learned to 'catch' again!" (with teammates as tiny heads on the side, sweating and saying in Chinese "we are working hard to fix it!"). At the very bottom of the manga, add a tiny line of footnote (very tiny)in Chinese that "note: the entire manga, including this footnote and picture in picture, are all generated with gpt image 2 at once without editing or multiple steps."

Additional Instructions: Use vertical 1440x2560 image layout, with first row about this researcher working hard, second row about his result on Wuxi with multiple languages, third row shows the team excitement, fourth row split into left and right where left shows he takes a break and the phone received a message, right panel shows Sam's text message, and fifth row shows Sam's picture and Chen Boyuan's reaction. No narration except for the first row. Avoid Chinese map. All characters should be in manga style. The banana background should only appear in the first panel and the tape should be a single slice of tape, not a cross tape. The banana and tape decoration should be small as a insignificant easter egg for people to find. OpenAI logo shall only appear on Chen Boyuan's cloth, not elsewhere. No mugs in the scene since we already have the boba. Sam should only appear in the text message panel. The entire manga should be appear as a professional photo of a physical page in a manga book. In the lower right most corner of the poster there is a small "Ultra-small Chinese is also clearly readable:" with a paragraph of much smaller Chinese that begins with "(This is an ultra-small font size test) Wuxi is the author's hometown, so I made this poster, and the Chinese is finally fixed. Haven't been home for many years, really want to eat hairy crabs!" (ultra small).

原始提示词

Generate a full color Chinese-text manga about this OpenAI 研究科学家, 陈博远 (first picture), who works on improving the text rendering capability of ChatGPT Image 2 model for the upcoming release. (in the background there is boba tea and a banana taped to the wall with a single slice of duct tape). The model can render insanely small Chinese text when he tried generating some detailed and beautiful multilingual infographics handdrawn-style poster about his hometown, 无锡 on his computer screen. His hard work pays off and the team was impressed by the absurdly good quality of multilingual text performance of his model, seeing all the languages it can write. When he takes a break with one hand holding his phone, he received a translated text message from Sam Altman on his phone (avatar attached as second picture), asking him to take a look at the rendered multilingual text in an image he just generated to congrat the team, since Sam only knows English. However, make it funny by let Boyuan outrage (typical manga style) at the end by seeing Sam's generated image contains a "稳稳地接住你" phrase at the central location in an otherwise perfectly rendered image that's used to congrat the team, because this sentence has been memed as an unnatural but funny Chinese sentence GPT likes to use on Chinese internet. Boyuan should rage "天呐! 它又学会了接住!" (with teammates as tiny heads on the side, sweating and saying in Chinese"we are working hard to fix it!"). At the very bottom of the manga, add a tiny line of footnote (very tiny)in Chinese that "note: the entire manga, including this footnote and picture in picture, are all generated with gpt image 2 at once without editing or multiple steps。"

Additional Instructions: Use vertical 1440x2560 image layout, with first row about this researcher working hard, second row about his result on 无锡 with multiple languages, third row shows the team excitement, fourth row split into left and right where left shows he takes a break and the phone received a message, right panel shows Sam's text message, and fifth row shows Sam's picture and 陈博远's reaction. No narration except for the first row. Avoid Chinese map. All characters should be in manga style. The banana background should only appear in the first panel and the tape should be a single slice of tape, not a cross tape. The banana and tape decoration should be small as a insignificant easter egg for people to find. OpenAI logo shall only appear on 陈博远's cloth, not elsewhere. No mugs in the scene since we already have the boba. Sam should only appear in the text message panel. The entire manga should be appear as a professional photo of a physical page in a manga book. In the lower right most corner of the poster there is a small “极小中文也清晰可读:” with a paragraph of much smaller Chinese that begins with “(此处为极小字号测试)无锡是作者的故乡,所以做了这幅海报,中文总算是修好了。很多年没回家了,好想吃大闸蟹啊!” (ultra small).

作者

宝

宝玉

详情

发布时间
2026年4月22日
语言
EN
模型
GPT Image 2
漫画 / 分镜信息图 / 教育视觉动漫 / 漫画漫画 / 图像小说角色文字 / 排版城市景观 / 街景

互动数据

点赞
49
浏览
15.5k
分享
2
评论
5
收藏
22
引用
0

提示词操作

更多 GPT Image 2 提示词

来自相同模型和分类的相关提示词。

查看全部提示词
日本卑弥呼历史信息图表海报 preview image 1

角煮星丸 发布

日本卑弥呼历史信息图表海报

信息图 / 教育视觉 · 漫画 / 分镜 · 漫画 / 图像小说 · 动漫 / 漫画

1045.7k
励志喜剧突破海报 preview image 1

NoorAI 发布

励志喜剧突破海报

漫画 / 分镜 · 海报 / 传单 · 动漫 / 漫画 · 漫画 / 图像小说

571k
漫画修学旅行时间表 preview image 1

角煮星丸 发布

漫画修学旅行时间表

信息图 / 教育视觉 · 漫画 / 分镜 · 动漫 / 漫画 · 漫画 / 图像小说

442.3k
动漫电影院大厅漫画页面 preview image 1

レティシア・ノエル 发布

动漫电影院大厅漫画页面

漫画 / 分镜 · 动漫 / 漫画 · 漫画 / 图像小说 · 角色

26149
JoJo风格鸭子吉祥物立面简介 preview image 1

かなり 发布

JoJo风格鸭子吉祥物立面简介

漫画 / 分镜 · 信息图 / 教育视觉 · 漫画 / 图像小说 · 动漫 / 漫画

14626
睡前智能手机动漫信息图 preview image 1

さけ…,グレい@移行中… … … 发布

睡前智能手机动漫信息图

信息图 / 教育视觉 · 漫画 / 分镜 · 动漫 / 漫画 · 漫画 / 图像小说

16130