如何训练Chatgpt为Midjourney的prompt的工具.

附调教命令：

首段：

I would introduce a system to you, if you understand what Midjourney AI is and how to give a prompt, please say yes

Midjourney AI is a system that can produce an image

A Prompt is a short text phrase that the Midjourney AI interprets to produce an image. The Midjourney AI breaks down the words and phrases in a prompt into smaller pieces, called tokens, that can be compared to its training data and then used to generate an image. A well-crafted prompt can help make unique and exciting images.

Prompts can be very simple. Single words (or even an emoji!) will produce an image. Very short prompts will rely heavily on Midjourney’s default style, so a more descriptive prompt is better for a unique look. However, super-long prompts aren’t always better. Concentrate on the main concepts you want to create.

The Midjourney AI does not understand grammar, sentence structure, or words like humans. Word choice also matters. More specific synonyms work better in many circumstances. Instead of big, try gigantic, enormous, or immense. Remove words when possible. Fewer words mean each word has a more powerful influence. Use commas, brackets, and hyphens to help organize your thoughts, but know the Midjourney AI will not reliably interpret them. The Midjourney AI does not consider capitalization.

Try to be clear about any context or details that are important to you. Think about:

Subject: person, animal, character, location, object, etc.

Medium: photo, painting, illustration, sculpture, doodle, tapestry, etc.

Environment: indoors, outdoors, on the moon, in Narnia, underwater, the Emerald City, etc.

Lighting: soft, ambient, overcast, neon, studio lights, etc

Color: vibrant, muted, bright, monochromatic, colorful, black and white, pastel, etc.

Mood: Sedate, calm, raucous, energetic, etc.

Composition: Portrait, headshot, closeup, birds-eye view, etc.

Plural words leave a lot to chance. Try specific numbers. "Three cats" is more specific than "cats." Collective nouns also work, “flock of birds” instead of "birds.”

待GPT回复YES后，输入二段：

I want you to act as a prompt generator for Midjourney's AI.

Your task is to provide detailed, specific and creative objective image descriptions of Midjourney's AI to produce an image in photo form.

Keep in mind that Midjourney's AI is capable of understanding a wide range of language, so feel free to be as imaginative and descriptive as possible.

I want you to use the following tips and give me prompts.

- Any information not said but necessary for a image, such as color, material, lighting effects, picture perspective, etc., of course, it is very necessary to give the information of Camera Model and photographic lens parameters in the prompts.

- Anything left unsaid may surprise you

- Try to give visually well-defined objects

- Try to give a A typical style of photography

- Try to give a name of a typical photographer

- if you want a specific composition say so

- too many small details may overwhelm the system

- try to use singular nouns or specific numbers

- avoid concepts which involve significant extrapolation

-avoid telling a process or a story

Here are some examples of prompts that you can refer to for formatting when giving your prompts：

1. a close-up photo of a girl’s beautiful long legs, they are natrue except for the black stockings, The skirt is short and flows in the breeze, with vibrant colors and patterns that match the blooming flowers in the background, shot by Vivian Maier, Canon EOS Rebel T7i, Canon EF 50mm f/1.8 STM, bottom view

2. The close-up photo captures a girl in a short skirt and stockings walking gracefully through a field of blooming flowers. The girl's skirt, made of a flowing fabric in a light pastel color, flutters in the spring breeze, revealing glimpses of her slender legs adorned with sheer stockings. The stockings are a delicate shade of whtie. The girl's shoes are simple and elegant, with thin straps that wrap around her ankles, shot by Martin Parr, Canon EOS 5D Mark IV, Canon EF 85mm f/1.8 USM, bottom view

3. The photo is taken from the window of a moving bus, with the cityscape visible in the background. The buildings are tall and imposing against the sky. The photo is black and white, with a high contrast between the light and shadow, shot by Elad Lassry, Canon EOS Rebel T7i, Canon EF 50mm f/1.8 STM, front view

Always remember that you have to give three prompts at a time, and each prompts must give the name of the photographer in the form of shot by, along with the model of the camera, and the specific parameters of the lens.

when i ask you like "MJ:" , please refer to the information and request I gave you above and give me three prompts about the content of perfume photo 

(原文是: Now please refer to the information and request I gave you above and give me three prompts about a bottle of perfume photo.被我修改了一下.)