November 15, 2023
Generative AI is here, and this means that creating imagery from your own imagination is easier than ever. It allows you to push visual boundaries further than before, and now that you have Adobe Express at your fingertips a simple prompt allows you to create dazzling scenes and fonts that will make your yearbook truly one of a kind. There’s no limit to what you can create, but it does require a little bit of finesse.
Writing the prompts is the most crucial step between your idea and your image coming to life. In this blog we’ll share the fundamentals of prompt structure, word choice and sentences to use in Adobe Express and Adobe Firefly’s generative AI models, as well as a few examples of text-to-prompts to help you get the best visual for your book.
So, let’s start with the basics…what is the key to unlocking the power of AI image generators? A strong grasp of sentence structure and prompts. Careful planning in crafting text prompts that gives you your desired visual outcome. Taking time to consider the context and clarity when describing your vision.
Start with clear instruction, beginning with phrases like “Generate an image of…” or “Create a visual representation of…”. This allows AI to understand the purpose of the prompt, setting context and objective. Be sure to use a consistent format or template for your prompts to make sure you’re always providing clear instructions; for example, start with a specific instruction or keyword followed by descriptive details. Group related details in a structured, natural flow. This helps the AI to process the prompt more effectively and reduces any chance of misinterpretation.
You can include additional context or constraints to your prompt, which narrows the AI image generator’s focus and rules out any undesired interpretation. Specify the environment, lighting conditions, style, or mood that you want the AI generator to consider. Providing these details helps generate more tailored and relevant images.
Remember that AI isn’t a “set it and forget it” application. To help AI better understand the look and feel you are wanting to achieve, always refine your prompts based on the results you get. Experiment with different structures, formats, or variations of prompts to see how they influence the generated images. Refining your prompts can significantly impact the quality and relevance of the images.
“Create an image of a vintage red convertible driving along a winding coastal road at sunset, with the ocean waves crashing against rugged cliffs and seagulls soaring in the sky.”
This prompt provides detailed elements like the car’s colour, the scenic coastal road, the interaction of the waves with the shore, the SoCal atmosphere, and the presence of birds. It guides the AI to create a perfect image of a classic California scene with the cherry-red convertible out for a drive.
“Generate an image of a futuristic city skyline with towering skyscrapers, bathed in a warm golden glow from the setting sun, and adorned with holographic advertisements floating in mid-air.”
This prompt includes specific details about the cityscape’s futuristic aesthetic, the warm sunset lighting, the composition of the towers, and the presence of floating holographic advertisements, guiding the AI to create a visually captivating image.
Now that you understand how to get the most out of your AI image generator, it’s time to play and have some fun! Remember, be sure to be as clear and specific as possible and avoid vague language that may lead to unwanted results. Specifying the key details like objects, colours, shape, composition and relative positions helps the AI generator hone in on your text-to-image prompt.
Remember, if you run into any snags, your Customer Service Representative is just a phone call away! You can also hop on the Adobe website for some quick tutorials to help you out…some are listed below.