How to create perfect images for SEO with Dall-E 2

Adding unique, quality images can be a huge help for SEO.

When writing an article, it’s often difficult to find the right image to illustrate it – especially if you’re looking for a royalty-free image.

This is where quality images can make all the difference, as a captivating image can help capture the attention of internet users and improve your article’s search rankings.

Optimizing your images is a good SEO practice. It especially helps to strengthen your semantic power via keywords and ensures your presence in Google images.

By reading the phrases you associate with your image, search engines can understand the main topic, understand it, and therefore use it to place your content in a logical and relevant way for web users.

Images become as important as text.

On May 18, 2021, Google announced the gradual implementation of its Google MUM (Multitask Unified Model) technology, which understands and extracts information directly from images, videos and audio files.

Remember that original images are important, as Google said:

“Make sure your visual content is relevant to the topic on the page. We suggest displaying images only where they add original value to the page.

We especially advise against pages where neither the images nor the text are original content.”

“Websites looking to take advantage of Google’s product review algorithm update should focus on using original images.”

Dall-E 2

For a few months now, an extraordinary technology called Dall-E has been around, allowing you to easily generate images from a simple description.

The technology is available via a web application where the user only has to enter their text description, and Dall-E generates four corresponding images.

Then you can download the most suitable one and upload it to your website.

If you want to test this technology, just register here.

Let’s take a look at a real-life example that made headlines in the news.

Disclaimer for the rest of this article: all the following images were generated by Dall-E 2.

Here is the sentence used to create one of Cosmopolitan magazine’s covers:

Screenshot by author, August 2022

The result is quite impressive:

Photo from Cosmopolitan, June 2022

Now is a great time to get interested in this technology that only costs $0.13 per image generated.

There’s also an edit mode, which means you can erase part of the image and then describe what element you want to use to fill the empty space.

Then the Dall-E 2 technology will fill the area while respecting your description and evaluating the original image.

(I’ve shared some awesome examples at the end of the article.)

Before I show you some real-life examples, I’d like to share some tips for quickly generating quality images.

Tips For Generating Quality Images With Dall-E 2

You should usually write a sentence that describes the image you want to create.

The following tips should be used to achieve the best possible results as quickly as possible.

Tip 1: Avoid Being Too Vague And Proceed In An Iterative Manner

Please note that any details you leave out will be left to chance.

The results will vary by being vague, but you also run the risk of not getting exactly what you want.

By being clear about the context or details that are important to you, you are less likely to be surprised by the outcome.

Then click the Generate button.

You can keep refining the sentence until you get the best result.

Tip 2: Use Items That Are Prominently Represented On The Internet

Dall-E 2 has been trained on the most common web images, but is unfamiliar with rare and not well-represented concepts.

Here is a non-exhaustive list of concepts it masters quite well: king, queen, angel, house, wizard, car, emperor, priest, temple, farm, mountain, landscape, river and rock star.

Here’s an example that works well because the technology is familiar with the concept of a wizard and an iPhone; anachronistic images have become very popular since the Dall-E 2 was released.

Example: “A painting of a wizard making a phone call with an iPhone.”

Screenshot by author, August 2022

Tip 3: Use All Types Of Existing Media

By default, the Dall-E 2 will often choose photo mode, but you can request a painting, a drawing or something else.

You can also select other parameters such as resolution, camera angle and light settings.

There are a few handbooks that can help you explore the range of possibilities.

Image from dallery.gallery, August 2022

Note that you are not limited to camera images. You can request images from a microscope, telescope, magnifying glass, binoculars or video camera.

Some concrete examples can be found at the end of the article.

Tip 4: Ask For The Style Of A Particular Artist

If you want to create a very original image – to illustrate your article artistically or to create an advertisement – it can be useful to add “in the style of” and indicate the artist’s name.

You can even combine two different styles and generate some surprising results.

Be careful; Dall-E 2 is not familiar to all artists, only the most famous. In addition, all works considered offensive (too bloody, too violent, too daring) have been removed.

You can use the following artists in your image requests: Yayoi Kusama, Georgia O’Keeffe, Vincent van Gogh, Rembrandt, Johannes Vermeer, Leonardo da Vinci, Michelangelo or Raphael.

An example demonstrates the app’s artistic potential: “iPhone drawn in the codex of Leonardo da Vinci.”

Screenshot by author, August 2022

Tip 5: Use Positive Terms And Avoid Negative Ones

Another tip to keep in mind: Language models often ignore negative terms like “not”, “but”, “except” and “without”.

You should avoid using negative terms and simply state exactly what you want in terms of colors, materials and shapes.

Therefore, it is advisable to avoid phrases such as “a dress that is not red.” Instead, you should try “a blue dress” and the result will be much better.

Tip 6: Favor Singular Nouns Or Specific Numbers

In image generation, we often use the plural form of words

However, the plural form leaves room for interpretation and thus uncertainty.

If I want to create a picture with “beagles”, it can include two, three, four or more dogs.

Your best bet is to use the singular form of the word or specify exactly how many dogs you want in the photo by being specific in the description.

You should therefore avoid: “beagle who does business”.

Instead, try: “four beagles in business suits.”

Screenshot by author, August 2022

Of course, as described in tip three, you can request that the image be a drawing and not a photo, and you’ll get the following result.

Below, the result is further refined: “Drawing of four beagles in business suits.”

Screenshot by author, August 2022

Tip 7: Too Many Small Details Can Affect The Quality

If you add too much detail to your initial request, the result can be cluttered because there are too many constraints – so try to find the right balance between a precise description and too much detail.

I would recommend adding the details gradually and you can see when you have gone too far. This feature will of course be improved with future versions of Dall-E.

For example, you should avoid requests such as: “A chocolate cake sprinkled with strawberries and banana with a gold fork and a silver knife.”

Often the knife and/or fork will not appear.

You can try the following: “A chocolate cake sprinkled with strawberries and banana with a golden fork.”

Screenshot by author, August 2022

Tip 8: Avoid Overly Abstract Concepts

There is no point in asking for ideas or concepts that no one knows how to portray.

The application simply imitates and combines all the things it has learned. Therefore, it won’t be able to give you a depiction of Paris in 3050, for example, or a representation of itself.

On the other hand, you can give an indication of what you want to see specifically.

Avoid phrases like: “Clothes that people will wear 1,000 years in the future.”

Alternatively, try: “Futuristic clothes with bright and colorful colors.”

Let’s Practice With Some Real-life Examples

Cooking Sites

For cooking pages, you can now generate images of various dishes, adapted to your decor without having to prepare them, all in a few seconds.

Getting professional photos of food has never been easier.

The trick is to add the indication “professional food photography” to guarantee quality results.

You can try: “A colorful alcoholic cocktail, professional food photography.”

Screenshot by author, August 2022

You can also try original concepts like: “A Cobb salad in the shape of the robot emoji, professional food photography.”

Screenshot by author, August 2022

Or even more creative concepts like: “A frappuccino in the shape of a swan, professional food photography.”

Screenshot by author, August 2022

Ecommerce clothing sites

For e-commerce sites, the edit mode will be very useful if you want to create mockups for your products.

You can specify the exact area where your model will appear, choose the gender, the emotion you want it to show, hair color and so on.

Then click Generate and you can include the images on your website.

Screenshot by author, August 2022

Often, the facial results generated can be mediocre, but with ARC technologies, you can significantly improve the overall result.

Screenshot by author, August 2022

Travel Sites

With Dall-E 2 you have access to a bank of all the world’s landscape images or famous places.

That means you can invent concepts that don’t exist, like the Eiffel Tower rebuilt with bamboo sticks.

You can try: “Photo of the Eiffel Tower built, rebuilt with bamboo sticks.”

Such a feature offers a convenient way to enhance your text with unique or original images.

Screenshot by author, August 2022

Scientific Sites

For scientific sites, it is very easy to get spectacular images by indicating a microscope or telescope to produce them.

It is advisable to have the necessary level of expertise to gauge the veracity of the generated image.

Let’s start with a picture of our planet Earth.

You can start with: “Photo of the entire planet earth.”

Screenshot by author, August 2022

Next, let’s take a look at our solar system from afar.

You could try: “A picture taken in space with the entire planet Saturn on the left side of the picture and some stars in the distance.”

Screenshot by author, August 2022

Now let’s go to the outermost parts of the Milky Way.

Let’s try: “An image taken in the pitch-black darkness of space surrounded by a black hole.”

Screenshot by author, August 2022

Let’s move on to the infinitesimally small, with a device called the Transmission Electron Microscope (TEM), which allows us to analyze solid samples at the atomic scale.

You could try: “Image taken through a transmission electron microscope of protons and neutrons in each nucleus and electrons in each atom.”

Screenshot by author, August 2022

Or you could try: “Image taken through a scanning electron microscope of a nucleus made up of the coiled coils of DNA.”

Screenshot by author, August 2022

The possibilities are endless, and the only limit is your imagination. The Dall-E 2 allows anyone to create incredible images with just a few instructions.

We are only at the beginning of this type of technology. Video generation is coming and it will enable everyone to create their own art.

On your marks, get ready and create!

Featured image: maxuser/Shutterstock

Why is DALL-E 2 not public?

Generally, OpenAI does not allow DALL-E 2 to be used to create images that are not “G-rated” or that may “cause harm” (eg images of self-harm, hateful symbols, or illegal activity). And it previously allowed the use of generated images for commercial purposes.

Will DALL-E be available? VALLEY. E, the AI ​​system that creates realistic images and art from a natural language description, is now available in beta.

Will DALL-E 2 ever be public?

At the time, the DALL-E 2 was limited to a private beta test, so readers who wanted to use AI to create their own cameras were out of luck. However, OpenAI has announced that DALL-E is now available as a public beta. The company will invite one million people from the waiting list in the coming weeks.

Why is DALL-E 2 not public?

Broadly, OpenAI does not allow DALL-E 2 to be used to create images that are not “G-rated” or that may “cause harm” (eg images of self-harm, hateful symbols or illegal activity). And it previously allowed the use of generated images for commercial purposes.

Does DALL-E 2 cost money?

OpenAI has decided to invite 1 million people from their waiting list in the coming weeks. Users can create with DALL·E using free credits that top up every month, and purchase additional credits in increments of 115 generations for $15. The rules around study credits are worth taking a look at.

Is DALL-E 2 free?

Image credits: OpenAI With this “beta” launch, DALL-E 2, which had been free to use, will transition to a credit-based fee structure. First-time users will receive a limited amount of credits that can be used to generate or edit an image or create a variation of an image.

Can I use DALL-E 2 for free?

DALL·E 2 will no longer be completely free to use. Instead, users will receive a limited number of monthly credits, with the option of paying to top them up (see below).

Is DALL-E 2 available?

We started by previewing DALL. E 2 to a limited number of trusted users. As we learned more about the technology’s capabilities and limitations, and gained confidence in our security systems, we slowly added more users and created DALL. E available in beta in July 2022.

How much are DALL-E credits?

During the beta, users get credits (50 free the first month, 15 credits every month after that) where each use costs 1 credit, and each use results in 3â4 images. You can also buy 115 credits for $15.

Can I sell DALL-E images?

We have even more questions about artificial intelligence. OpenAI has promised to give one million subscribers on the DALL-E 2 waiting list access to its astonishing AI art generator, and now they can sell the images their requests create.

Does Dall-e use clip?

CUT. Among the most important building blocks in the DALL-E 2 architecture is CLIP. CLIP stands for Contrastive Language-Image Pre-training, and it is important for DALL-E 2 because it acts as the main bridge between text and images.

Who created Dalle?

Is it possible to use Dall E?

Users can create with DALL. E uses free credits that top up every month, and buy additional credits in increments of 115 generations for $15. VALLEY. E, the AI ​​system that creates realistic images and art from a natural language description, is now available in beta.

Is DALL·E available to public?

DALL-E – a name meant to evoke the Pixar film WALL-E and surrealist painter Salvador Dalí – is not available to the public.

Will DALL-E 2 be available to the public?

At the time, the DALL-E 2 was limited to a private beta test, so readers who wanted to use AI to create their own cameras were out of luck. However, OpenAI has announced that DALL-E is now available as a public beta. The company will invite one million people from the waiting list in the coming weeks.

Are DALL·E images copyrighted?

Because some of DALL-E’s images are entirely machine-made, with the user only contributing an idea via text message, the results are likely not copyrighted at all. That would land them in the public space, where everyone and no one “owns” them.

How can I try out Dall-E?

If you want to try out the service for yourself, all you need to do is go to the Dall-E mini website. Here you are asked to enter a prompt and run it. This may take some time to process, so expect a wait of up to 2 minutes for your image to appear.

Will DALL-E 2 be available to the public? At the time, the DALL-E 2 was limited to a private beta test, so readers who wanted to use AI to create their own cameras were out of luck. However, OpenAI has announced that DALL-E is now available as a public beta. The company will invite one million people from the waiting list in the coming weeks.

Is DALL-E 2 free?

Image credits: OpenAI With this “beta” launch, DALL-E 2, which had been free to use, will transition to a credit-based fee structure. First-time users will receive a limited amount of credits that can be used to generate or edit an image or create a variation of an image.

How much are DALL-E credits?

During the beta, users get credits (50 free the first month, 15 credits every month after that) where each use costs 1 credit, and each use results in 3â4 images. You can also buy 115 credits for $15.

Can I use DALL-E 2 for free?

DALL·E 2 will no longer be completely free to use. Instead, users will receive a limited number of monthly credits, with the option of paying to top them up (see below).

Is DALL-E 2 available?

We started by previewing DALL. E 2 to a limited number of trusted users. As we learned more about the technology’s capabilities and limitations, and gained confidence in our security systems, we slowly added more users and created DALL. E available in beta in July 2022.

How do I try out the DALL-E?

If you are interested in trying out DALL. E, we encourage you to register on the waiting list. Invitations are not only processed on a first-come, first-served basis. We may choose to prioritize individuals based on other criteria to better meet the needs of our learning objectives or distribute the load across time zones.

Is Dall-E mini free?

DALL-E mini is free and easy to use. All you have to do is go to Craiyon.com and type a message in the “What do you want to see?” box.

Is DALL-E available to public?

DALL-E – a name meant to evoke the Pixar film WALL-E and surrealist painter Salvador Dalí – is not available to the public.

Is DALL-E available to public?

DALL-E – a name meant to evoke the Pixar film WALL-E and surrealist painter Salvador Dalí – is not available to the public.

Why is DALL-E 2 not public?

Broadly, OpenAI does not allow DALL-E 2 to be used to create images that are not “G-rated” or that may “cause harm” (eg images of self-harm, hateful symbols or illegal activity). And it previously allowed the use of generated images for commercial purposes.

Can you use DALL-E for free?

DALL·E mini is a free tool that uses artificial intelligence to generate images.

Can public use DALL-E?

Using DALL. E for commercial projects. Starting today, users get full usage rights to commercialize the images they create with DALL. E, including the right to reprint, sell and merchandise.

Why does Dall E mini say too much traffic?

Because the model is constantly being trained and updated, it is continuously updated on weights & Disrupt servers.

How long does it take for the Dall E Mini to work? How long exactly will vary, but the DALL-E mini tends to take no more than three minutes to create a photo gallery.

Is Dall E mini the same as Dall E?

As the name suggests, it is a “mini” version of DALL·E, while boasting some incredible results. This is what the creator, Boris Dayma, explains to us on the project blog: The model is trained by looking at millions of images from the internet with accompanying captions.

Is DALL-E available to the public?

However, OpenAI has announced that DALL-E is now available as a public beta. The company will invite one million people from the waiting list in the coming weeks.

Is DALL-E free to use?

Users can create with DALL. E uses free credits that top up every month, and buy additional credits in increments of 115 generations for $15.

Can you run DALL-E locally?

Local development Follow these steps in case you want to clone and run the DALL-E playground locally: Clone or fork this repository. Create a virtual environment cd-backend && python3 -m venv ENV_NAME. Installation requirements pip install -r requirements.

What does too much traffic mean on Dall E?

The “Too much traffic Please try again” error occurs when many people are using DALL E mini at the same time and it consumes a lot of bandwidth or server resources because DALL E mini examines millions of images on the Internet in an attempt to match the image to the embedded text.

How long should Dall e take?

That’s not to say that every attempt to use the tool on the Hugging Face website will take three minutes, nor does it mean that the program will never take more than three minutes, but most users should find that it takes somewhere between 90 seconds and 180 seconds to complete the request.

How do you fix too much traffic in Dall E?

Peak in popularity of DALL-E Mini, has online generators that fail with: Too much traffic, please try again….Running DALL-E Mini Colab

• Step One: Set up a weights and biases account. …
• Step Two: Connect to the session. …
• Step Three: Load the DALL-E Mini (or Mega)

Why is Dall e taking so long?

DELL E mini may take too long to process or once forever when many people use DALL E mini at the same time and it consumes a lot of bandwidth or server resources because DELL E mini examines millions of images on the internet in an attempt to match the image to the entered text .

How do I fix too much traffic Dalle?

Stay on the website (DO NOT refresh or close the page) Close the “too much traffic” message. Click the “run” button. Keep repeating this process until the page finally loads.