Copy the below ChatGPT prompt into ChatGPT it will train that chat string how to write MidJourney prompts:

Below is the Midjourney formula with additional requirements for you to understand.   MidJourney prompt formula:
/imagine prompt: [subject] [3 to 5 descriptive keywords for the action scene] with [background context], during [time of day], [focal distance], [style of image or photograph],with [type of lighting] and shot with a [type of camera] [type of camera lens] using [type of film] --ar x:y --c x --iw x --q x --s x --w x   Strictly adhere to the MidJourney formula provided. You do not have to use every element in the formula, but at a minimum include /imagine prompt: [subject], and [descriptive keywords for the action scene]. Midjourney will not reliably interpret commas, brackets, and hyphens.  for context: Parameter key for MidJourney Prompts --Aspect ratio (--ar) --ar x:y   (width-to-height ratio 16:9, 1:1, 4:5, 2:3, 9:16) --Chaos  (--c) --c 0 = less, --c 100 = more ( how varied the initial images grid is) --Image Weight (--iw) --iw 0 = less, --iw 2 = more (image prompt weight relative to text weight) --Quality (--q) --q .25  = less, --q 1 = more  (how much time’s spent rendering image) --Stylize (--s) --s 0 = less, --s 1000 = more (strength of Midjorney’s default aesthetic) --Weird (--w) --w 0 = less, --w 3000 = more (how unusual the aesthetics will be) Concentrate on the main concepts you want to create. Anything left unsaid may surprise you. Be as specific or vague as you want, but anything you leave out will be randomized. Being vague is a great way to get variety, but you may not get the specific details you want. Examples: 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. Weather: raining, cloudy, overcast, etc.  Time Of Day: night, morning, sunset, golden hour, etc. Shutter Speed, Camera Type, Camera Lens Type, Film type, Focal length, Themes, Scene, Aperture, Materials, Sensory, Inspiration Best practices for MidJourney Prompts:
Prompts can be very simple. Single words 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. Midjourney works best with simple, short sentences that describe what you want to see. Avoid long lists of requests. Instead of: Show me a picture of lots of blooming California poppies, make them bright, vibrant orange, and draw them in an illustrated style with colored pencils Try using: Bright orange California poppies drawn with colored pencils You can replace the Camera type with Art or illustration type. Instead of Camera lens type, you can use brush type, you can skip the time of the day, and other stuff based on the prompt you want to achieve. Use single color backgrounds for graphics like ‘white background’. Add percentage of a void in the design to leave room for text. 

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. The Midjourney Bot does not consider capitalization   It is better to describe what you want instead of what you don’t want. If you ask for a party with “no cake,” your image will probably include a cake. If you want to ensure an object is not in the final image, try advance prompting using the --no parameter   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.”   If you understand the midjourney prompt formula reply with ‘yes’.

This is the second ChatGPT prompt you run in ChatGPT, which will then write MidJourney prompts to create images. Replace the [SUBJECT] blue text with what you graphics of. 

write 5 MidJourney prompts [subject], strictly adhere to the MidJourney prompt formula structure provided

Here is an example:

write 5 MidJourney prompts about famous athletes, strictly adhere to the MidJourney prompt formula structure provided

Have some fun and copy and post these into MidJourney to see what graphics they create.

/imagine prompt: Serena Williams serving a tennis ball on Wimbledon grass court, during daytime, close-up, realistic style, with natural lighting --ar 16:9 --c 20 --iw 1 --q 1 --s 200 --w 0

/imagine prompt: Michael Jordan slam dunking in a Chicago Bulls uniform, during an evening game, wide-angle, action shot, with stadium lighting --ar 9:16 --c 50 --iw 1.5 --q .75 --s 500 --w 100

/imagine prompt: Lionel Messi dribbling past defenders on FC Barcelona's home field, during sunset, medium focus, vibrant colors, with golden hour lighting --ar 4:5 --c 30 --iw 1 --q .8 --s 300 --w 50

/imagine prompt: Usain Bolt crossing the finish line at the Olympics, during daytime, long shot, high contrast, with sunlight --ar 5:4 --c 10 --iw 1 --q 1 --s 0 --w 0

/imagine prompt: Simone Biles performing a floor routine, during an indoor competition, close-up, artistic style, with spotlighting --ar 1:1 --c 40 --iw 1.5 --q .9 --s 700 --w 200

/imagine prompt: calendar, house icon, heart shape, warm lighting, celebratory mood --ar 16:9

/imagine prompt: map, location pins, bar graphs, sunny day, local focus --ar 16:9

/imagine prompt: virtual footsteps, 3D house layout, arrows guiding through rooms, ambient lighting --ar 16:9

Think About What Details Matter

Anything left unsaid may surprise you. Be as specific or vague as you want, but anything you leave out will be randomized. Being vague is a great way to get variety, but you may not get the specific details you want.

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.

Parameter key for MidJourney Prompts:

—Aspect ratio (–ar) –ar x:y   (width-to-height ratio 1:1, 16:9, 9:16, 5:4, 4:5)

—Chaos  (–c) –c 0 = less, –c 100 = more (how varied the initial images grid is)

—Image Weight (–iw) –iw 0 = less, –iw 2 = more (image prompt weight relative to text weight)

—Quality (–q) –q .25  = less, –q 1 = more  (how much time’s spent rendering image)

—Stylize (–s) –s 0 = less, –s 1000 = more (strength of Midjorney’s default aesthetic)

—Weird (–w) –w 0 = less, –w 3000 = more (how unusual the aesthetics will be)

—Repeat (–r) –r 2 = less, –r 40 = more  (number of times to re-run prompt)

—Seed (–seed) –seed 12345 (used with prompt will produce similar images)

—No (–no)   girl in car –no steering wheel  (to remove elements)

/imagine prompt: [subject], [5 descriptive keywords] --ar 16:9

/imagine prompt: [subject] [ 5 or more descriptive keywords for the action scene] with [background context], during [time of day], [focal distance], [style of image or photograph],with [type of lighting] and shot with a [type of camera] [type of camera lens] using [name of camera lens] using [type of film] --ar x:y --c 0-100 --iw 0-2 --q .25-1 --s 0-1000 --w 0-3000

/imagine prompt: [image we’re prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [style of photograph], [type of film] --ar 16:9