August 5, 2024
How to Market Your Cause With AI Images
AI images, tools, and the art of creating
The details are in the prompt. AI text-to-image makes it super easy for anyone to create art. Now that anyone can create art, you should focus on making images that really stand out — and for this, all you need is the prompt and your imagination.
AI models are packed with massive amounts of knowledge. To get them to do things of higher ground, one needs to know the science of prompting.
Created with Midjourney. Imagining a high tech, high nature future.
I’ve been using Midjourney since it launched and have used it to design a book cover, course certificate, my blog — you name it. I even played around with Stable Diffusion in its early days. When I started, I created tons of bad images. But slowly, with time and practice, I got better at prompting and learned the art of creating beautiful images with AI.
What’s an AI image
It’s just an image like any other on your computer — except it was created by an AI using a prompt. A prompt is a text description of what you want the AI to create, and there’s a bit of an art in getting the prompt right.
It’s all about the prompt
If your prompt is a one-liner like “create a cheetah in African savanna,” the AI uses its imagination to fill in the rest — which might not end up looking as good as what you wanted. When you have a specific image in mind, describe it in as much detail as you can. Imagine you have an artist sitting with you and you’re telling them exactly what to draw — the color choices, lighting, vibe, concept, style. If you want it to look like a specific style, mention that clearly.
Created with Flux.
Describe every little detail — the background, color of the sky, the position of the cheetah, the expression, the scene, time of day, the photo angle, style. AI takes your detailed description into account to create the image. Your output will then look closer to what you want.
Prompt: A sleek, muscular cheetah stands alert on a sun-drenched savanna. Golden afternoon light, piercing amber eyes gaze intently into the distance. In the background, the vast African grasslands stretch to the horizon. Acacia trees dot the landscape. Capture the cheetah from a low angle, slightly below eye level — creating a sense of power and majesty.
Make updates or fixes in seconds. You can change an AI image in real time. Simply change the word and you change how the image looks. And the best part — you can create just about any art whenever you want, in an instant. Some tools like Midjourney let you create variations of the generated images or use them within the prompt as a sort of image prompt. There are more advanced concepts like in-painting — where you select a part of an existing image and use the prompt to change it (like putting a crown on a person’s head).
AI image tools
Midjourney, DALL·E, and Flux are amazing text-to-image AI models. My personal favorites are Midjourney and Flux — the visuals are realistic. DALL·E is inside ChatGPT and Bing. Many creator tools have incorporated AI into their services — Canva, Substack, Descript, etc.
How to create epic image prompts
These are two of my prompt hacks for better outputs.
Reuse prompts. Never start with a prompt from scratch. Look for inspiration by exploring AI art and see the prompts behind it. I use that prompt as a base to iterate on.
Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word “ACT NOW” is painted over the eyes — white bold strokes with visible texture.
Use chatbots. I use chatbots to craft image prompts. I have a conversation with Claude or ChatGPT on the concept I have in mind. I go into a long conversation about what I’m looking for and ask the chatbot to help me describe the image prompt. I also seek advice on camera angles and other technical aspects. I use that as my prompt and iterate from there.
I plan to post more how-to guides on AI for regens.
If you have questions, reach out here or on X.
Originally published on Substack — read the original →.
