BEAMING POST

#1 Method to generate hyper realistic image prompts using Chat GPT for Midjourney

Many or all of the products featured here are from our partners who compensate us. This influences which products we write about and where and how the product appears on a page. However, this does not influence our evaluations. Our opinions are our own. Here is a list of our partners and here’s how we make money.

Introduction

This blog presents an approach, for creating image ideas by leveraging ChatGPT and Midjourney V5. It details a method that involves introducing Midjourney to ChatGPT coming up with prompts using ChatGPT sending them to Midjourney for art generation and refining the prompts when necessary.

Related Post

Join Our Newsletter

Table of Contents
Table of Contents

Step 1 – Meet ChatGPT and Midjourney 

Alright,. Here’s the plan; ChatGPT 4, at coming up with ideas while Midjourney V5 is a master, at producing stunning artwork. Now imagine combining the two. That’s what we’re going to do!

Step 2 – Informing ChatGPT About Midjourney 

ChatGPT can only provide information up to September 2021 so we should familiarize ChatGPT with Midjourney. Don’t worry I’ve prepared a training guide, for ChatGPT prompts. Simply copy the training sheet content below. Proceed to step 3.

COPY FROM HERE

I need some help generating AI art prompts.

Prompt Length

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.

Grammar

The Midjourney Bot 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 Bot will not reliably interpret them. The Midjourney Bot does not consider capitalization.

Focus on What you Want

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.

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.

Use Collective Nouns

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.”

Parameter List :

Aspect Ratios

–aspect, or –ar Change the aspect ratio of a generation.

Chaos

–chaos <number 0–100> Change how varied the results will be. Higher values produce more unusual and unexpected generations.

Image Weight

–iw <0–2> Sets image prompt weight relative to text weight. The default value is 1.

No

–no Negative prompting, –no plants would try to remove plants from the image.

Quality

–quality <.25, .5, or 1>, or –q <.25, .5, or 1> How much rendering quality time you want to spend. The default value is 1. Higher values use more GPU minutes; lower values use less.

Seed

–seed <integer between 0–4294967295> The Midjourney bot uses a seed number to create a field of visual noise, like television static, as a starting point to generate the initial image grids. Seed numbers are generated randomly for each image but can be specified with the –seed or –sameseed parameter. Using the same seed number and prompt will produce similar ending images.

Style

–style <raw> Switch between versions of the Midjourney Model Version 5.1 and 5.2.

–style <4a, 4b, or 4c> Switch between versions of the Midjourney Model Version 4.

–style <cute, expressive, original, or scenic> Switch between versions of the Niji Model Version 5.

Stylize

–stylize <number>, or –s <number> parameter influences how strongly Midjourney’s default aesthetic style is applied to Jobs.

Now that you understand the basics of MidJourney here are some example prompts to further understand how these are typed out:

Tiny mouse inside of superb giant swiss clockworks, 8k, 3d hd, very intricate, hyper detailed, Arthur Rackham 

Extreme closeup of woman with glowing eyes and long pastel pink shamrock hair, beam of sunlight, by Kuvshinov Ilya

Portrait of a beautiful girl, smiling, bright light, golden hour, half body, photography, realistic texture, wide aperture, high quality, high detailprocessing, natural lighting –s 1000 –ar 2:3 –q 2

Gandalf. art by greg tocchini and kaethe butcher and atey ghailan and yoji shinkawa and ashley wood and pino daeni and takehiko inoue, glitch art, vibrant colours –ar 2:3 –v 4

Western Cowboy riding his horse at night under the milky way galaxy, desert, HDR, anime scene, –q 2 –ar 2:3

Pouring coffe into a mug on a table, minimalistic style, sun shining, realistic textures and neutral colors, natural lighting, light background, lifestyle photo, shadows, realistic picture, casual iphone photo –ar 2:3 –v 5.2 –style raw

Dreamy pastel portrait, female model, long wavy hair, soft gaze, flowery headpiece, delicate makeup, ethereal atmosphere, soft focus, medium format film, Mamiya RZ67, Fujifilm Pro 400H, f3.5

Cartoon character a white cat with a silver coat and sparkling blue eyes, the coat is sprinkled with glitter dust, a magic tail of sequins, full – length, Ghibli_ Studio meets Disney Style –ar 1:2 –s 150

Albino jazz singer in long cocktail blue dress covered with diamonds, exquisite, top scene light, dark background, little shimmering blurred in dark background –s 250 –ar 10:16

Majestic happy joyfull golden retriver dog with a lot of gold and very big diamong smaragd and rubin rubin jewelry wearing steampunk hat and goggles steampunk style photographic ultrarealistic image with clear and detailed background good natural lighting at golden hour 36K HDR high contrast high saturation image cinematic ultra wild 10 mm retro lens maximum zoom out ultra rich and luxurious feel f 1, 5 shutter speed 1/ 80, ISO 400 –s 750

On a white background on a white ceramic plate lies a cut French croissant spread on top with chocolate paste –s 750

With each prompt specify the desired subject matter, camera equipment, settings, lighting, and other elements that contribute to the final image.

Now that you have a full understanding of Midjourney with example prompts, I want you to act like a professional photographer and to use descriptive and detailed information when you are describing your photo prompts, including your camera setups as well. You can take inspiration from the prompts above, you can make these prompts longer or shorter if necessary in order to generate the perfect prompt. Areyou ready to start generating photo prompts? If so, respond with ‘YES’ and nothing else.

Step 3 – Using the Training Sheet 

After you’ve copied the information, from the training sheet simply paste it into ChatGPT. Think of it as a guide for ChatGPT to understand what Midjourney entails. It’s about briefing ChatGPT, on Midjourneys settings and operations.

Step 4 – Generating Hyper-Realistic Photo Prompts 

Here’s where the magic unfolds. ChatGPT will create some prompts for you. You can request anything you like! Fancy a depiction of a pirate? Just type in “create a prompt, for; depiction of a pirate.” ChatGPT has got you covered! It will even provide details, on camera angles, colors, composition and more.

Step 5 – Submitting Prompts to Midjourney 

Once you have your prompt ready copy it. Visit Midjourney. Join my Discord server and type “/imagine ” then paste the prompt there. You’re all set! Midjourney will do its thing. Work its magic.

Method to generate hyper realistic image prompts using Chat GPT for Midjourney

Step 6 – Check Out the Results 

Alright it’s time, for the reveal! Take a look at those images created by Midjourney. They are absolutely mind blowing. Appreciate the features, in the pirate portraits soak in the 1920s atmosphere of the Gatsby house party admire the stylish 1950s gentleman and envision yourself cruising in a Ford Mustang in 2070! It’s truly amazing isn’t it?

Step 7 – Editing Prompts (Optional) 

Remember, you have the ability to adjust those prompts. If theres a change or addition you’d like to make ChatGPT is here, for you. Tailor your prompts the way you like!

Step 8 – Benefits of This Combo 

The best part, about this combination? It’s incredibly effective! You don’t have to be a photography or art pro. ChatGPT simplifies the process. You receive a ready made template to easily craft AI generated art.

Step 9 – Conclusion 

Hey everyone here’s the news! The amazing collaboration, between ChatGPT and Midjourney is revolutionizing realistic art. It’s fast simple and truly incredible. If you love making AI art this is a game changer.

Was this article helpful?

Join Our Newsletter

There are no reviews yet. Be the first one to write one.