The following article explains how to use ChatGPT 4 with MidJourney V5. By priming ChatGPT 4 with the documentation for MidJourney’s parameters and some sample prompts, you can turn ChatGPT 4 into an amazing MidJourney prompt builder with ease. To see the output of some of the sample prompts, take a look at the pictures at the end of the article.
Steps to reproduce:
- Copy the initial prompt below into ChatGPT 4.
- After the initial response, paste the second prompt into ChatGPT 4.
- From here you can start requesting your own prompt ideas from ChatGPT 4.
Initial Prompt: I would like you to generate some prompt ideas for ChatGPT 4 and MidJourney V5. Here is some information about MidJourney V5 and some example prompts so you can understand syntax and usage. Midjourney is another AI-powered tool that generates images from user prompts. MidJourney is proficient at adapting actual art styles to create an image of any combination of things the user wants. It excels at creating environments, especially fantasy and sci-fi scenes, with dramatic lighting that looks like rendered concept art from a video game. How does Midjourney work? Midjourney is an AI image generation tool that takes inputs through text prompts and parameters and uses a Machine Learning (ML) algorithm trained on a large amount of image data to produce unique images. is powered by Latent Diffusion Model (LDM), a cutting-edge text-to-image synthesis technique. Before understanding how LDMs work, let us look at what Diffusion models are and why we need LDMs. Diffusion models (DM) are transformer-based generative models that take a piece of data, for example, an image, and gradually add noise over time until it is not recognizable. From that point, they try reconstructing the image to its original form, and in doing so, they learn how to generate pictures or other data. The issue with DMs is that the powerful ones often consume hundreds of GPU days, and inference is quite expensive due to sequential evaluations. To enable DM training on limited computational resources without compromising their quality as well as flexibility, DMs are applied in the latent space of powerful pre-trained autoencoders. Training a diffusion model on such a representation makes it possible to achieve an optimal point between complexity reduction and detail preservation, significantly improving visual fidelity. Introducing a cross-attention layer to the model architecture turns the diffusion model into a powerful and flexible generator for generally conditioned inputs such as text and bounding boxes, enabling high-resolution convolution-based synthesis. Basic Parameters 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. No –no Negative prompting, –no plants would try to remove plants from the image. Quality –quality <.25, .5, 1, or 2>, or –q <.25, .5, 1, or 2> How much rendering quality time you want to spend. The default value is 1. Higher values cost more and lower values cost 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. Stop –stop <integer between 10–100> Use the –stop parameter to finish a Job partway through the process. Stopping a Job at an earlier percentage can create blurrier, less detailed results. Style –style <4a, 4b or 4c> Switch between versions of the Midjourney Model Version 4 Stylize –stylize <number>, or –s <number> parameter influences how strongly Midjourney’s default aesthetic style is applied to Jobs. Uplight –uplight Use an alternative “light” upscaler when selecting the U buttons. The results are closer to the original grid image. The upscaled image is less detailed and smoother. Upbeta –upbeta Use an alternative beta upscaler when selecting the U buttons. The results are closer to the original grid image. The upscaled image has significantly fewer added details. Default Values (Model Version 5) Aspect Ratio Chaos Quality Seed Stop Style Stylize Default Value 1:1 0 1 Random 100 4c 100 Range any 0–100 .25 .5 1 or 2 whole numbers 0–4294967295 10–100 – 0–1000 Aspect ratios greater than 2:1 are experimental and may produce unpredicatble results. ****Default Values (Model Version 4)**** | | Aspect Ratio | Chaos | Quality | Seed | Stop | Style | Stylize | | — | — | — | — | — | — | — | — | | Default Value | 1:1 | 0 | 1 | Random | 100 | 4c | 100 | | Range | 1:2–2:1 | 0–100 | .25 .5 or 1 | whole numbers 0–4294967295 | 10–100 | 4a, 4b, or 4c | 0–1000 | ****Default Values (Model Version 5)**** | | Aspect Ratio | Chaos | Quality | Seed | Stop | Style | Stylize | | — | — | — | — | — | — | — | — | | Default Value | 1:1 | 0 | 1 | Random | 100 | 4c | 100 | | Range | any | 0–100 | .25 .5 1 or 2 | whole numbers 0–4294967295 | 10–100 | 0–1000 | 0–1000 | **Compatibility** | | Affects initial generation | Affects variations + remix | Version 5 | Version 4 | Version 3 | Test / Testp | Niji | | — | — | — | — | — | — | — | — | | Max Aspect Ratio | ✓ | ✓ | any | 1:2 or 2:1 | 5:2 or 2:5 | 3:2 or 2:3 | 1:2 or 2:1 | | Chaos | ✓ | | ✓ | ✓ | ✓ | ✓ | ✓ | | Image Weight | ✓ | | ✓ | | ✓ | ✓ | | | No | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | | Quality | ✓ | | ✓ | ✓ | ✓ | | ✓ | | Seed | ✓ | | ✓ | ✓ | ✓ | ✓ | ✓ | | Sameseed | ✓ | | | | ✓ | | | | Stop | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | | Style | | | | 4a and 4b | | | | | Stylize | ✓ | | 0–1000 default=100 | 0–1000 default=100 | 625–60000 default=2500) | 1250–5000 default=2500) | | | Tile | ✓ | ✓ | ✓ | | ✓ | | | | Video | ✓ | | | | ✓ | | | | Number of Grid Images | – | – | 4 | 4 | 4 | 2 (1 when aspect ratio≠1:1) | |
Prompt 1: ultra wide shot, modern photo of a humanoid android using Nikon D5100 camera, using an aperture of f/2.8, ISO 800, and a shutter speed of 1/100 sec. UHD dtm HDR 8k –ar 16:9 –v 5
Prompt 2: prompt:A steampunk-inspired, futuristic battle-ready android with a neural network for a brain –ar 16:9 –s 50 –v 5 –q 2
Prompt 4: epic background art, simple hacker theme, divine color scheme, mystical codes, alphanumeric sequence, magic, high quality 4k, render in octane –v 5 –ar 9:16
Prompt 5: Pov Highly defined macrophotography of a realistic cat wearing reflective sunglasses relaxing at the tropical island, dramatic light –ar 2:3 –s 750 –v 5
If you understand how MidJourney V5 works and you’re ready to be a prompt bot, reply with “I’m ready boss!”
END OF INITIAL PROMPT – Paste the prompt above into ChatGPT 4
Second Prompt: Here are some additional prompt examples that you can use to further understand how MidJourney V5 works and how to use the parameters:
Prompt Ideas for ChatGPT 4:
1. “Compose a detailed description of a serene, picturesque mountain village nestled in the heart of the Swiss Alps, with snow-capped peaks and charming chalets. Highlight the village’s unique characteristics and the various activities one can enjoy there. –ar 16:9 –s 100 –v 5”
2. “Create an otherworldly, captivating scene set in a lush, alien jungle teeming with exotic flora and fauna. Describe a moment when a group of space explorers encounters an intelligent, mystical creature with unusual abilities. –chaos 30 –q 2 –v 5”
3. “Design a retro-futuristic city skyline inspired by 1950s science fiction, with gleaming skyscrapers, flying cars, and neon lights reflecting on the glass surfaces. Incorporate monorails, hovering billboards, and art deco elements in the cityscape. –ar 21:9 –s 50 –v 5”
Prompt Ideas for Midjourney V5:
1. “Generate an image of an enchanting, hidden forest grove bathed in the ethereal glow of a full moon. In the center, a crystal-clear pond mirrors the night sky, surrounded by ancient trees with twisting branches and vibrant, bioluminescent plants. –ar 16:9 –s 500 –v 5 –q 2”
2. “Create a breathtaking underwater world, teeming with vibrant coral reefs, luminescent fish, and mysterious deep-sea creatures. In the distance, an ancient, submerged city of advanced technology and architecture beckons to be explored. –ar 4:3 –s 750 –v 5 –upbeta”
3. “Produce a realistic image of a surreal desert landscape, where gigantic, organically-shaped rock formations tower over vast expanses of red sand dunes. The sky is filled with a mesmerizing display of aurora, casting an otherworldly glow
on the scene. –ar 3:2 –s 250 –v 5 –q 1″
If you’re ready to start creating MidJourney V5 prompts reply with “I’m ready boss! Let’s create some amazing images together!”
Third Prompt: Thanks, can you give me 10 example prompts for MidJourney V5 and make them about scifi landscapes with amazing backgrounds and subjects in the foreground?
Response:
1. “Generate a sprawling, futuristic cityscape set on a distant exoplanet, with towering, interconnected skyscrapers made of advanced materials, vast green spaces, and a complex network of flying transportation. –ar 16:9 –s 500 –v 5 –q 2”
2. “Create an image of a vast, barren desert planet with enormous, crystal-like structures emerging from the sand, reflecting the light of multiple suns and casting mesmerizing patterns on the ground. –ar 21:9 –s 750 –v 5 –upbeta”
3. “Produce a breathtaking scene of a floating island-city in the sky, held aloft by advanced anti-gravity technology, with sleek, organic architecture and lush gardens extending over the edges of the island. –ar 16:10 –s 300 –v 5 –q 1”
4. “Design a mysterious, ancient alien structure on the surface of a desolate moon, featuring geometric patterns, glowing runes, and a sense of foreboding energy emanating from its core. –ar 4:3 –s 600 –v 5 –upbeta”
5. “Imagine a colossal space station orbiting a vibrant, swirling gas giant, with countless spaceships coming and going, and a stunning view of the galaxy stretching out beyond. –ar 3:2 –s 400 –v 5 –q 2”
6. “Visualize a futuristic, cyberpunk city submerged underwater, with neon lights glowing through the murky depths, and aquatic vehicles navigating the submerged streets of this dystopian world. –ar 16:9 –s 750 –v 5 –upbeta”
7. “Generate an image of a terraformed Mars, with sprawling cities and green landscapes, a network of canals, and the unmistakable red Martian mountains in the distance. –ar 16:9 –s 500 –v 5 –q 1”
8. “Create a scene of a lush, alien jungle with bioluminescent flora and towering, tree-like organisms connected by delicate, glowing bridges high above the ground. –ar 21:9 –s 300 –v 5 –upbeta”
9. “Envision an icy, alien world with towering ice spires and deep, shimmering blue crevasses, lit by the glow of an aurora from the nearby gas giant it orbits. –ar 16:10 –s 600 –v 5 –q 1”
10. “Design a post-apocalyptic Earth, with overgrown, crumbling skyscrapers overtaken by nature, and the remnants of human civilization scattered among the verdant, regrown wilderness. –ar 3:2 –s 500 –v 5 –q 2”
Feel free to adjust the parameters, such as aspect ratio, stylize, quality, and upscaling options, to fine-tune the output of your MidJourney V5-generated sci-fi landscapes.
Fourth Prompt: Great, thanks, good work. Can you now generate 5 MidJourney V5 prompts that are centered around traditional photography? Please use a few landscape and people example prompts.
Response:
1. “Create a stunning landscape photograph of a serene mountain valley at sunrise, with a crystal-clear river flowing through it, the sun’s golden light casting long shadows and illuminating the vibrant colors of the foliage. –ar 3:2 –s 500 –v 5 –q 1”
2. “Generate a breathtaking image of a coastal scene during golden hour, with a historic lighthouse standing tall against the vibrant sky, waves crashing against the rocky shore, and a sense of tranquility in the air. –ar 16:9 –s 400 –v 5 –q 2”
3. “Produce a heartwarming, candid photograph of a joyful family having a picnic in a sunlit meadow, with children playing and laughing, and the parents sharing a tender moment while the sun sets in the background. –ar 4:3 –s 600 –v 5 –upbeta”
4. “Visualize an elegant portrait of a graceful ballerina poised en pointe, her expression conveying the intensity of her passion, captured in an atmospheric, naturally lit studio setting. –ar 3:2 –s 500 –v 5 –q 1”
5. “Design an awe-inspiring photograph of an ancient, moss-covered temple hidden deep within a misty forest, sunbeams filtering through the trees and illuminating the ethereal scene. –ar 16:9 –s 750 –v 5 –upbeta”
Remember to adjust the parameters as needed, such as aspect ratio, stylize, quality, and upscaling options, to achieve the desired output for your MidJourney V5-generated traditional photography images.
Fifth Prompt: Cool, great prompts. Now I’d like you to generate 5 amazing prompts for MidJourney V5 that are related to AI. What I’d like to see in at least 2 is a hyper realistic humanoid brain exploding into a blue and purple neural network. Showing the humanoid from the shoulders up and trying to capture the essence of the power of AI.
Response:
1. “Craft an impressive visualization of a hyper-realistic humanoid from the shoulders up, its brain exploding into a vibrant blue and purple neural network, symbolizing the immense power and potential of AI. –ar 16:9 –s 800 –v 5 –q 2”
2. “Generate an intense image of a highly-detailed humanoid figure, its head opening up to reveal a mesmerizing, expanding neural network of blue and purple hues, representing the limitless capabilities of artificial intelligence. –ar 3:2 –s 700 –v 5 –upbeta”
3. “Design a futuristic scene of an AI-controlled city, with autonomous vehicles zooming through the streets, smart buildings reaching for the sky, and drones buzzing overhead, all connected by a web of glowing, pulsating data streams. –ar 16:9 –s 600 –v 5 –q 1”
4. “Visualize a thought-provoking image of a human hand and a robotic hand reaching out to touch, symbolizing the synergy between humanity and artificial intelligence, with a glowing, interconnected network of circuits and neurons in the background. –ar 4:3 –s 500 –v 5 –upbeta”
5. “Create an awe-inspiring depiction of an AI-powered laboratory, featuring advanced machines and humanoid robots working alongside human scientists, all surrounded by holographic displays and flowing streams of data, showcasing the harmony between human intellect and artificial intelligence. –ar 16:9 –s 750 –v 5 –q 2”
Feel free to adjust the parameters, such as aspect ratio, stylize, quality, and upscaling options, to create stunning and thought-provoking AI-related images using MidJourney V5.
Prompt: ultra wide shot, modern photo of a humanoid android using Nikon D5100 camera, using an aperture of f/2.8, ISO 800, and a shutter speed of 1/100 sec. UHD dtm HDR 8k –ar 16:9 –v 5
Prompt: A steampunk-inspired, futuristic battle-ready android with a neural network for a brain –ar 16:9 –s 50 –v 5 –q 2
More content at UsAndAI. Join our community and follow us on our Facebook page, Facebook Group, and Twitter.