The power of DALL‑E artificial intelligence (now in its second generation known as DALL‑E 2) allows anyone to generate completely unique images that have never been seen before. By simply providing a clear AI image cue, Microsoft Designer enables users to bring their ideas to life.
Like any emerging technology, DALL‑E opens up exciting new possibilities but also requires a bit of experimentation to achieve optimal results.
Note: These suggestions for creating AI-generated art are applicable both to Microsoft Designer and the DALL‑E site. The advantage of using Designer is that it not only generates unique images based on provided ideas but also provides additional design elements such as text or graphics, as well as AI-powered editing experiences for seamless integration into a design.
Steps to create an image with DALL‑E and Microsoft Designer
Using DALL‑E to generate images is deceptively simple. In fact, it's as simple as completing two steps:
- Visit Microsoft Designer
- In the text box labeled "Start with an AI-generated image," enter a phrase describing the desired image to generate—an AI image prompt
What can you write in the text box? Anything!
You can generate a wide range of images, including simple icons, patterns, illustrations, artwork, and even depictions of imaginary 3D objects or photos.
For the purposes of this article, let's imagine we want to generate materials to promote a running club. Let's type in "an adorable character running, ink-and-watercolor illustration, colorful background" and see the results:
Not bad for the first attempt, right?
Tips for writing an effective AI image prompt for DALL‑E
To get the most out of DALL‑E, the quality of the image prompt matters. In short, it's best to imagine the image already exists in an online gallery and write a short caption that might accompany it.
Provide specific details
Using a single word like "runner" may result in a wide range of images, from elite athletes winning marathons to cute sketches of children running through meadows—or even imaginative creatures. Instead of using a single word, use a descriptive phrase to convey what you're looking for. Consider including the following details in your search phrases:
- Specific details about objects or characters
- Information about the setting or background
- The medium style, such as oil painting, Polaroid photo, or marble statue
- Additional adjectives like "colorful," "swirling," "playful," "happy," "minimalist," "geometric," "vibrant," "dramatic," "ornate," "austere," or any other adjective that helps define the desired aesthetic
Add directive details
Instead of simply specifying the medium style as "oil painting," you can provide more specific details like "oil-on-canvas masterpiece by Caravaggio from 1599." Instead of requesting a "photograph," you can ask for an "HD photograph taken with a Canon camera, studio lighting, large-format portrait on Kodak ColorPlus 200 film."
Including these additional details in your image prompts helps the AI technology narrow down the type of image you want, even if it doesn't always get it exactly right.
Avoid potential issues
AI generation has its limitations, so certain types of image prompts are less likely to achieve the desired effect. Here are a few things to avoid in your descriptions:
- Complex scenes with multiple subjects
- Detailed layout requests, such as specifying the position of multiple objects
- Images with multiple faces (as they often end up distorted)
- Requests for text in the image (as the generator is not proficient in spelling)
Why use AI to generate an image?
Given the abundance of existing images, you might wonder why it's worth generating your own using DALL‑E. Here are a few reasons:
Create an original image
Generating an image ensures that it's completely unique and has never been seen or used before. It offers the opportunity to showcase something truly distinctive for yourself or your brand.
Let your imagination soar
Combine various subjects, settings, and art styles to create captivating and intriguing combinations that capture your audience's attention. A koala bear detective or a marble sculpture of a cartoon character? Anything is possible!
Depict imaginary individuals
With generated images, you can include human representations in your creative work without needing real models or signed release forms.
Develop a signature look
By reusing specific style keywords while varying the subjects, you can create multiple related images over time, resulting in a unique and consistent visual identity for your brand.
For example, if you design content for a mental health blog, you can use a consistent description like "geometric Bauhaus illustration from 1963" to generate a series of related images.
The images above were all generated using variations of that phrase:
- Fearful face, anxiety, scrunched eyes, geometric Bauhaus illustration from 1963
- Sad face, gloomy, depression, hopelessness, geometric Bauhaus illustration from 1963
- Calm face, eyes closed, meditating, geometric Bauhaus illustration from 1963
- Sleeping figure, restful, Zs, snooze, geometric Bauhaus illustration from 1963
Generating diverse image styles with AI image prompts
When it comes to generating images, being knowledgeable about how to describe various elements is crucial. To ask for something, you need to be able to describe it!
Discovering the names of interesting art styles can be a part of the fun. Since AI generation tools are trained on real images, there's no need for convoluted descriptions—normal phrasing is sufficient. You can draw inspiration from online research sources, gallery websites, and art textbooks. The possibilities are endless.
Let's explore an array of examples for our fictional running club.
Experiment with different art mediums
There are numerous ways to make marks on paper, from watercolors to airbrushing. Mentioning the art medium or technique in your image prompts can yield distinctive results.
The four images shown above were generated using the following prompts:
- A woman running through the park, charming, cozy watercolor illustration on a white background
- A speedy jogger, happy expression, airbrush caricature
- A runner leaping over an obstacle, cute, detailed pencil sketch
- Portrait of a determined athlete, dramatic, acrylic on canvas, outstanding masterpiece
Consider using these words and phrases for different art styles: "stencil art," "crayon," "chalk," "etching," "oil paintings," "ballpoint pen," "colored pencil," "Chinese watercolor," "pastels," "woodcut," "charcoal," "screen print," "photocollage," "storybook illustration," "newspaper cartoon," "vintage illustration from the decade."
Achieve a digital aesthetic
For a more contemporary feel, you can generate illustrations with a digital look.
The four images shown above were generated using the following prompts:
- A happy child jogging, cute 3D illustration in the style of Pixar, octane 3D render, volumetric lighting, green background
- A man running through the city in the 1980s, retro pixel art, screenshot from an SNES game
- A woman running, athletics, stylish vector art, gradients, vibrant colors, graphic design
- A smiling man jogging, joyful, face, front-on view, vector illustration, sticker art
Try incorporating these phrases for different digital styles: "digital art," "vector graphics," "minimalist," "geometric," "isometric," "2.5D," "matte clay," "digital painting," "screenshot from a favorite game or animation," "diagram," "instruction manual."
Embrace retro and artistic styles
You can draw inspiration from the entirety of art history to achieve your desired style. Generate anything from ancient cave paintings to 20th-century modern art and give your piece a vintage twist.
Your description might include specific years, art movements, mediums, or famous artists. And while you're at it, you can describe it as a "masterpiece," "masterwork," or an "outstanding example of..."—it never hurts to ask.
The four images above were generated using the following prompts:
- Marathon runners, detail from a decorative Minoan mural, artifact from 2000 BCE
- Beautiful Renaissance painting of a running man, athletics, oil-on-canvas masterpiece by Michelangelo, dramatic, dark background
- A group of runners on the starting line, art deco design, 1925, vintage, streamline moderne
- Female athlete running over a bridge, vibrant, ethereal post-impressionist painting on canvas by Cézanne
Explore other art styles like "surrealism," "Dadaism," "metaphysical painting," "orphism," "cubism," "suprematism," "De Stijl," "futurism," "expressionism," "realism," "Bauhaus," "color field painting," "impressionism," "baroque," "rococo," "mannerism," "ancient Egyptian papyrus," and "ancient Roman mosaic."
Create faux-tography
If you desire a more realistic-looking image, you can describe it as a photograph.
In this case, your description may include references to lighting, time of day, angle, distance ("close-up," "low camera angle"), and technical details like camera type and lens. For example, a photo taken with a Canon DSLR using a 35mm lens will produce different results from a flash photo taken with a disposable camera.
The four images above were generated using the following prompts:
- A magical running shoe, futuristic, stunning product studio photography, low-key lighting, bokeh, smoke effects
- A proud Latino man athlete celebrating victory, close-up with specific facial details, candid photo portrait, sports photojournalism
- Double exposure of silhouette runners jogging, lush green verdant trees, and forest texture
- A runner tying their laces, Instax Kodachrome photography, low camera angle, fish-eye lens
Experiment with other photography-related terms like "trail cam," "CCTV," "VHS," "Polaroid," "infrared photography," "daguerreotype," "cyanotype," "photo from a favorite magazine or website," "film still from [famous film]," "color splash," "extreme close-up," "wide-angle lens," "telephoto lens," "light leaks," "Lomography," "autochrome," "camera phone," "camera obscura," "warm lighting," "long exposure," "fast shutter speed," "backlighting," "low-key lighting," "golden hour," "blue hour," "macro lens," "motion blur," "shallow depth-of-field," "action photography," and "candid portrait."
Create objects
Although the generated images are two-dimensional, you can still describe and generate representations of three-dimensional artwork. When crafting your image prompt, it may be helpful to envision how the object would appear in a photograph. This allows you to reference lighting, backgrounds, lenses, and other factors to achieve the desired effect.
The four images above were generated using the following prompts:
- A triumphant female marathon runner as a beautiful bronze statue, outstanding public art, tourist attraction, glowing in sunlight during the golden hour, captured with a 4K HD DSLR Nikon
- A cute jogging character running, amigurumi, beautiful craft project, purple background, studio photography
- Runners in a road race depicted as a detailed diorama, fine modeling, captured with macro photography using a tilt-shift lens
- A brave runner portrayed within a snow globe, festive collectible, exquisite glass ornament, studio photography, sparkly dark background
Experiment with alternative materials like "felt," "tapestry," "knitting," "embroidery," "papercraft," "origami," "pop-up books," "modeling clay," "porcelain," "ceramics," "terracotta," "metalwork," "jewelry," "crystal," "fiberglass," and even "butter."
Write an AI image prompt and start creating!
It truly is that simple! The key is to experiment and explore the realm of possibilities. You're bound to generate fantastic images along with some playful mistakes along the way.
In the examples above, we focused on runners, but you can generate images of any subject—buildings, interior designs, costume designs, imaginary monsters, unusual landscapes, and more.
As you delve deeper into this creative process, you might find yourself researching famous art movements, learning about various film stocks, or exploring architectural glossaries in order to craft even more inventive descriptions.
I can't wait to see what you create—why not give it a try?
Source
