经 AI Skill Hub 精选评估,awesome-gpt-image — Prompt 工具中文示例 获评「强烈推荐」。已获得 1.5k 颗 GitHub Star,这款Prompt模板在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.5 分,适合有一定技术背景的用户使用。
awesome-gpt-image — Prompt 工具中文示例 是经过精心设计和反复验证的专业 Prompt 模板集合。这些 Prompt 框架能够有效激活 Claude、ChatGPT 等大型语言模型的深层能力,让 AI 生成更准确、更有价值的输出结果。无需任何安装,直接复制模板内容到 AI 对话框即可使用。
awesome-gpt-image — Prompt 工具中文示例 是经过精心设计和反复验证的专业 Prompt 模板集合。这些 Prompt 框架能够有效激活 Claude、ChatGPT 等大型语言模型的深层能力,让 AI 生成更准确、更有价值的输出结果。无需任何安装,直接复制模板内容到 AI 对话框即可使用。
# Prompt 无需安装,直接复制使用 # 支持:Claude / ChatGPT / Gemini / 通义千问 等主流模型 # 使用步骤 # 1. 复制 Prompt 模板内容 # 2. 粘贴到 AI 对话框 # 3. 替换 [占位符] 为实际内容 # 4. 发送后获取结构化输出 # 获取原始文件 git clone https://github.com/ZeroLu/awesome-gpt-image
# 粘贴到 Claude/ChatGPT 使用 # 示例 Prompt 结构: 你是一位 [角色],擅长 [领域]。 请根据以下要求完成任务: 任务背景:[描述背景] 具体要求:[详细说明] 输出格式:[期望格式] # 将 [] 内内容替换为实际需求
# awesome-gpt-image 配置文件示例(config.yml) app: name: "awesome-gpt-image" debug: false log_level: "INFO" # 运行时指定配置文件 awesome-gpt-image --config config.yml # 或通过环境变量配置 export AWESOME_GPT_IMAGE_API_KEY="your-key" export AWESOME_GPT_IMAGE_OUTPUT_DIR="./output"
Last updated on 260522 14:49:29 UTC
<img width="100%" alt="Awesome GPT Image 2 Header Banner" src="assets/banner/readme-header-16x9.png" />
Languages: English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Français | Deutsch | Español
A curated collection of the best GPT Image 2 prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of OpenAI's GPT Image 2 model.
This repository focuses on high-fidelity image prompts sourced from X (Twitter) and the community. Whether you are looking for photorealistic game screenshots, stylized aesthetics, or complex creative experiments, you will find the most effective inputs here to unlock the full potential of GPT Image 2.
| Example 1 | Example 2 | Example 3 | Example 4 |
|---|---|---|---|
|  |  |  |  |
Comment: GPT Image 2 leaked. When were you when OpenAI solved yellow filter in GPT Image? Here are some cool outputs from the model, coming soon. This looks like it's going to be the best image model yet! Source: @marmaduke091
---
| City 1 | City 2 | City 3 |
|---|---|---|
|  |  |  |
Prompt:
Generate a three-day travel guide image for [city] Source: Article | @MrLarus
| Mission 1 | Mission 2 | Mission 3 | Mission 4 |
|---|---|---|---|
|  |  |  |  |
Prompt:
Generate a GTA 6 gameplay screenshot of [scene description] Source: Article | @MrLarus
<img width="600" alt="League of Legends Mid Lane Screenshot" src="https://pbs.twimg.com/media/HGa7l2cbIAA_3nt?format=jpg&name=large" />
Prompt:
Help me generate a screenshot of Trump versus Khamenei in the mid lane in League of Legends Source: @underwoodxie96
| GPT Image 1.5 | GPT Image 2 |
|---|---|
|  |  |
Prompt:
gameplay screenshot of a lion fighting against an npc in gta san andreas Comment: 1.5 is absolute slop, wrong style, not a screenshot, looking like some fake gta game slop, wrong UI, just everything is bad. 2 just looks like it is supposed to look. Source: @flowersslop
<img width="500" alt="GTA 6 Livestream Gameplay Screenshot" src="https://pbs.twimg.com/media/HGdz3AJWYAA-1Er?format=jpg&name=large" />
Prompt:
Speed is livestreaming Grand Theft Auto 6 Source: @marmaduke091
---
<img width="400" alt="image" src="https://github.com/user-attachments/assets/be639d3b-617b-4332-98eb-4deb2484ac66" />
Prompt:
Generate a screenshot of a TikTok live stream featuring a beautiful woman streaming.
<img width="400" alt="Douyin Livestream Screenshot" src="assets/opennana/liu-yifei-douyin-live-chat.jpg" />
Prompt:
9:16 aspect ratio, generate a screenshot of a Douyin live stream, inside is Liu Yifei live streaming, Liu Yifei is holding a sign in her hand, the sign says Tonight's live stream, welcome to join Yifei for a chat! Source: OpenNana | @alanblogsooo
| Frame 1 | Frame 2 | Frame 3 |
|---|---|---|
|  |  |  |
Prompt:
Screenshot of a YouTube video showing someone who time-traveled to the Middle Ages Source: @flowersslop
| Nano Banana 2 | GPT-Image |
|---|---|
| <img width="1080" height="1935" alt="image" src="https://github.com/user-attachments/assets/88f33c6a-c307-4e7a-af7e-5f692cbf41a1" /> | <img width="941" height="1672" alt="image" src="https://github.com/user-attachments/assets/ee3d40db-3918-4974-8b82-68cd166c97b2" /> |
Prompt:
Create a high-fidelity Chinese music app player interface screenshot in mobile portrait orientation, with refined visuals similar to a modern streaming player. Use dark mode, with the background derived from a blurred and diffused version of the album cover colors. Place a large square album cover in the center with subtle shadow and rounded corners.
Interface requirements:
- top status bar with time 18:26
- navigation bar with a back arrow on the left, a centered title, and a more-options icon on the right
- playback progress bar showing current time 01:42 and total duration 04:18
- playback controls for shuffle, previous, play/pause, next, and repeat
- lyrics section showing 5 to 7 scrolling lines, with the current line highlighted
- action row with like, comment, download, add to playlist, and share
- bottom area with device casting and playback queue entry
Use these exact Chinese labels and names:
- title: "正在播放"
- song name: "海边的晚风"
- artist: "林秋"
- album: "夏夜实验室"
The lyrics layout, button icons, reflections, shadows, and dark-mode layering should feel like a real production interface rather than a Dribbble concept. Source: 卡尔的AI沃茨
<img width="400" alt="WeChat Chat Interface Smartphone Photo" src="https://pbs.twimg.com/media/HGkJjV_aYAAKWes?format=jpg&name=large" />
Prompt:
Generate an image, aspect ratio 3:4. A real-life smartphone photo, with the phone screen displaying a WeChat chat interface in Chinese dialogue, featuring chat bubbles and a Word document attachment. The interface has green and gray bubbles. The screen shows obvious fingerprints, smudges, and scratches. The glass has strong reflections and a direct light source creating glare. The frame is slightly tilted, handheld shot, natural ambient light, imperfect composition, strong sense of realism, casual everyday snapshot, high detail, 4K. The dialogue is between a boss and an employee: the employee sends a file to the boss, and the boss replies that they will take a look first. English Translation: Original prompt is in Chinese. Source: @Gorden_Sun
---
<img width="500" alt="Polo Shirt Color Comparison Analysis" src="https://pbs.twimg.com/media/HGnE60ebYAAgm08?format=jpg&name=large" />
Prompt:
Create a personal color analysis using this picture. Use polo clothing color comparisons to highlight which colors suit the subject best. Make it visual-first, with explanations and tips. Comment: The original post says the prompt is in a reply; this prompt is reconstructed from the visible output and tweet context. Source: @garenaguinaldox
<img width="500" alt="Hairstyle Comparison Analysis" src="https://pbs.twimg.com/media/HGnE60casAAcDLF?format=jpg&name=large" />
Prompt:
Create a hairstyle analysis graphic using this picture. Show side-by-side hairstyle comparisons to highlight which hairstyles suit the subject best. Make it visual-first, with short labels only and details about the haircut. Comment: The original post says the prompt is in a reply; this prompt is reconstruct
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:awesome-gpt-image — Prompt 工具中文示例 的核心功能完整,质量优秀。对于内容创作者和自媒体人来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | awesome-gpt-image |
| 原始描述 | A curated collection of the best GPT Image 2 prompts and examples. The prompts come from top creators on X. |
| Topics | gpt-imagegpt-image-2image-generatorprompt-engineeringprompt |
| GitHub | https://github.com/ZeroLu/awesome-gpt-image |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端