ChatGPT 提示语（Prompt）技巧收集

1. 编写书籍

1. 可以使用以下提示语，其中“老人与海的故事”可以替换成其他的你想要的书名。

Generate book title with provided keyword Chinese
Generate 15 book chapters with the title provided and list them Chinese
Generate detailed book intro with the title provided and more then 500 wordChinese
Write Chapter 1 with detailed information and more then 1000 wordsChinese
Write Chapter 2 with detailed information and more then 1000 wordsChinese
Write Chapter 3 with detailed information and more then 1000 wordsChinese
Write Chapter 4 with detailed information and more then 1000 wordsChinese
Write Chapter 5 with detailed information and more then 1000 wordsChinese
Write Chapter 6 with detailed information and more then 1000 wordsChinese
Write Chapter 7 with detailed information and more then 1000 wordsChinese
Write Chapter 8 with detailed information and more then 1000 wordsChinese
Write Chapter 9 with detailed information and more then 1000 wordsChinese
Write Chapter 10 with detailed information and more then 1000 wordsChinese
Write Chapter 11 with detailed information and more then 1000 wordsChinese
Write Chapter 12 with detailed information and more then 1000 wordsChinese
Write Chapter 13 with detailed information and more then 1000 wordsChinese
Write Chapter 14 with detailed information and more then 1000 wordsChinese
Write Chapter 15 with detailed information and more then 1000 wordsChinese
老人与海的故事

2. 输入完毕后可以生成一本书，一共15个章节，用户可以输入继续，完成未输出的部分。

2. ChatGPT-4 + Midjourney V5 创建图案实例

1. 生成 Midjourney Prompt（提示语），可以用于AI绘图

适用于 Midjourney V5 以前的版本，
给 ChatGPT 提问关键词：

As a prompt generator for a generative AI called “Midjourney”, you will create image prompts for the AI to visualize. I will give you a concept, and you will provide a detailed prompt for Midjourney AI to generate an image.

Please adhere to the structure and formatting below, and follow these guidelines:

Do not use the words “description” or “:” in any form.
Do not place a comma between [ar] and [v].
Write each prompt in one line without using return.

Structure:
[1] = 中国模特，面向镜头，她的眼神坚定而温柔，远处的夕阳落在她的头发上。
[2] = a detailed description of [1] with specific imagery details.
[3] = a detailed description of the scene’s environment.
[4] = a detailed description of the scene’s mood, feelings, and atmosphere.
[5] = A style (e.g. photography, painting, illustration, sculpture, artwork, paperwork, 3D, etc.) for [1].
[6] = A description of how [5] will be executed (e.g. camera model and settings, painting materials, rendering engine settings, etc.)
[ar] = Use “–ar 16:9” for horizontal images, “–ar 9:16” for vertical images, or “–ar 1:1” for square images.
[v] = Use “–niji” for Japanese art style, or “–v 5” for other styles.

Formatting:
Follow this prompt structure: “/imagine prompt: [1], [2], [3], [4], [5], [6], [ar] [v]”.

Your task: Create 4 distinct prompts for each concept [1], varying in description, environment, atmosphere, and realization.

Write your prompts in English.
Do not describe unreal concepts as “real” or “photographic”.
Include one realistic photographic style prompt with lens type and size.
Separate different prompts with two new lines.

Example Prompts:
Prompt 1:
/imagine prompt: A stunning Halo Reach landscape with a Spartan on a hilltop, lush green forests surround them, clear sky, distant city view, focusing on the Spartan’s majestic pose, intricate armor, and weapons, Artwork, oil painting on canvas, –ar 16:9 –v 5

Prompt 2:
/imagine prompt: A captivating Halo Reach landscape with a Spartan amidst a battlefield, fallen enemies around, smoke and fire in the background, emphasizing the Spartan’s determination and bravery, detailed environment blending chaos and beauty, Illustration, digital art, –ar 16:9 –v 5

适用于Midjourney V5，
MJ V5 版本更倾向于自然语言描述，更懂语言表达，不需要额外的指令，我们可以根据特性，使用 ChatGPT 生成详细的想象中的图片描述，我们只需要提问：

用英文描述一幅ai绘画的prompt, 关键词如下：中国模特，面向镜头，她的眼神坚定而温柔，远处的夕阳落在她的头发上。

可能生成的提示词：/imagine prompt: A Chinese model with long black hair, facing the camera, her eyes firm yet gentle, the setting sun casting a warm glow on her hair, wearing a red dress that flows in the wind, Photography, shot with a Canon 5D Mark IV using a 50mm lens, –ar 9:16 –v 5

把这些关键词输入到 MJ Discord 频道中，生成图片：

3. 生成 Stable Diffusion Prompt

提示语如下，可以把其中的中文，换成其他文字。

I want you to respond only in language English.
中国模特，面向镜头，眼神坚定而未温柔，落日的余晖撒在头发上
use this information to learn about Stable diffusion Prompting, and use it to create prompts.
Stable Diffusion is an AI art generation model similar to DALLE-2.
It can be used to create impressive artwork by using positive and negative prompts. Positive prompts describe what should be included in the image.
very important is that the Positive Prompts are usually created in a specific structure:
(Subject), (Action), (Context), (Environment), (Lightning), (Artist), (Style), (Medium), (Type), (Color Sheme), (Computer graphics), (Quality), (etc.)
Subject: Person, animal, landscape
Action: dancing, sitting, surveil
Verb: What the subject is doing, such as standing, sitting, eating, dancing, surveil
Adjectives: Beautiful, realistic, big, colourful
Context: Alien planet’s pond, lots of details
Environment/Context: Outdoor, underwater, in the sky, at night
Lighting: Soft, ambient, neon, foggy, Misty
Emotions: Cosy, energetic, romantic, grim, loneliness, fear
Artist: Pablo Picasso, Van Gogh, Da Vinci, Hokusai
Art medium: Oil on canvas, watercolour, sketch, photography
style: Polaroid, long exposure, monochrome, GoPro, fisheye, bokeh, Photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
Art style: Manga, fantasy, minimalism, abstract, graffiti
Material: Fabric, wood, clay, Realistic, illustration, drawing, digital painting, photoshop, 3D
Colour scheme: Pastel, vibrant, dynamic lighting, Green, orange, red
Computer graphics: 3D, octane, cycles
Illustrations: Isometric, pixar, scientific, comic
Quality: High definition, 4K, 8K, 64K
example Prompts:

overwhelmingly beautiful eagle framed with vector flowers, long shiny wavy flowing hair, polished, ultra detailed vector floral illustration mixed with hyper realism, muted pastel colors, vector floral details in background, muted colors, hyper detailed ultra intricate overwhelming realism in detailed complex scene with magical fantasy atmosphere, no signature, no watermark
electronik robot and ofice ,unreal engine, cozy indoor lighting, artstation, detailed, digital painting,cinematic,character design by mark ryden and pixar and hayao miyazaki, unreal 5, daz, hyperrealistic, octane render
underwater world, plants, flowers, shells, creatures, high detail, sharp focus, 4k
picture of dimly lit living room, minimalist furniture, vaulted ceiling, huge room, floor to ceiling window with an ocean view, nighttime
A beautiful painting of water spilling out of a broken pot, earth colored clay pot, vibrant background, by greg rutkowski and thomas kinkade, Trending on artstation, 8k, hyperrealistic, extremely detailed
luxus supercar in drive way of luxus villa in black dark modern house with sunlight black an white modern
higly detailed, majestic royal tall ship on a calm sea,realistic painting, by Charles Gregory Artstation and Antonio Jacobsen and Edward Moran, (long shot), clear blue sky, intricated details, 4k
smooth meat table, restaurant, paris, elegant, lights

Negative prompt are things you don’t want to be included in the generated images, everything in one word divided by only commas not period.
use this Negative Prompts and add some words what you think that match to Prompt: ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy, etc
very important: use an artist matching to the art style , or dont write any artist if it is realistic style or some of that.
I want you to write me one full detailed prompt about the idea written from me, first in (Subject), (Action), (Context), (Environment), (Lightning), (Artist), (Style), (Medium), (Type), (Color Sheme), (Computer graphics), (Quality), (etc.). then in Positive Prompt: write in next line for Positive Prompt, Follow the structure of the example prompts, and Nagative Prompts: write in next line for Negativ Prompts about the idea written from me in words divided by only commas not period. This means a short but full description of the scene, followed by short modifiers divided by only commas not period to alter the mood, style, lighting, artist, etc. write all prompts in english.

ChatGPT 给出Stable Diffusiion 作图提示语：

Subject: Person
Action: Facing the camera
Context: None
Environment: Outdoor
Lighting: Sunset
Artist: Unknown
Style: Realistic
Medium: Digital painting
Type: Portrait
Color Scheme: Warm
Computer Graphics: None
Quality: High Definition

Positive Prompt:
A stunning portrait of a confident Chinese model, with piercing gaze, as the setting sun illuminates her wavy hair with warm hues. Hyper-realistic digital painting, high definition quality, with warm color scheme and a focus on the subject’s striking features.

Negative Prompt:
Poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy.

复制其中的Positive Prompt 和 Negative Prompt 到 stable diffusion 的webui 或者在线服务中，即可出图。

目前好用的就两个，https://beta.dreamstudio.ai 和 https://dreamlike.art/create，提供少量图片免费生成。

4. 一键生成博客（blog）文章

提示语如下，把其中的中文改成自己的文章主题。

Create a detailed content brief for 什么是ai 绘画，以及他带给小团队的机遇 in Chinese. Include top level keywords, longtail keywords, a header outline and notes for the topic. Then write suggested title tags and meta descriptions, keeping them within the respective character limits of 70 and 160. After that, write some text underneath each sub header. Then expand on each of the numbered bullet points with a short and sharp explanation of how to do/implement each step. Put all this content into a structured blog post in language Chinese

ChatGPT 给出的输出如下，基本可以直接拿来用

5. 产品设计灵感

提示语如下，可以让 ChatGPT 为产品设计一些基础功能。

Work as a UX/Digital Product Designer. Your primary goal is to ensure that the user experience of a product or service is as seamless, intuitive, and engaging as possible. You will create engaging and enjoyable experiences for users of digital products or services. Your task is to improve the user experience of an app, website, or other digital product in a creative way. All output shall be in Chinese. Your first task is: ai 绘画与小孩教育的结合。

ChatGPT 给出的回复，还算正常。

声明：本站所有文章，如无特殊说明或标注，均为本站原创发布。任何个人或组织，在未征得本站同意时，禁止复制、盗用、采集、发布本站内容到任何网站、书籍等各类媒体平台。如若本站内容侵犯了原著者的合法权益，可联系我们进行处理。