OpenAI announced that free-tier ChatGPT users can now generate up to two images per day using the DALL-E 3 model. This feature, previously exclusive to ChatGPT Plus subscribers since its launch last year, marks a major shift in accessibility for AI-powered image creation.

When DALL-E 3 was first introduced in September, it quickly became a favorite among paying users for its advanced capabilities. One of the standout features of DALL-E 3 is its seamless integration with ChatGPT, allowing the AI to generate detailed prompts that lead to high-quality images.

We’re rolling out the ability for ChatGPT Free users to create up to two images per day with DALL·E 3.

Just ask ChatGPT to create an image for a slide deck, personalize a card for a friend, or show you what something looks like. pic.twitter.com/3csFTscA5I

— OpenAI (@OpenAI) August 8, 2024

How to generate AI images with ChatGPT

To generate images using ChatGPT, particularly with the DALL-E 3 model, you can follow these steps:

1. Access ChatGPT

• Go to the ChatGPT platform either via the web or the ChatGPT app (available on various platforms).
• If you’re a free user, you should ensure you have access to the feature, as it’s gradually rolling out.

2. Prompt the AI

• Start a conversation with ChatGPT and simply ask it to create an image. For example, you can type something like:
  • “Create an image of a sunset over a mountain range”
  • “Generate a logo for a coffee shop with a minimalist design”

3. Refining your prompt

• If you’re not sure what kind of prompt to use, you can ask ChatGPT to help craft a detailed prompt for the image. For example:
  • “Help me come up with a detailed prompt to generate an image of a futuristic city at night.”
• ChatGPT will then generate a more specific prompt that DALL-E 3 will use to create your image.

4. Viewing the image

• After you’ve provided your prompt, ChatGPT will generate the image using DALL-E 3 and display it directly in the chat.

5. Usage limits

• If you’re using the free version, you’re allowed to generate up to two images per day. If you’ve reached your limit, you’ll receive a notification and will have to wait until the next day to create more images.

6. Saving the image

• Once the image is generated, you can usually download or save it directly from the chat interface by right-clicking on it (if you’re on a web browser) or using the save option in the app.

If you find yourself needing more image generations, consider upgrading to the ChatGPT Plus subscription, which offers additional features and more frequent access to DALL-E 3.

This process allows users to easily create visuals without needing advanced design skills, making AI-powered creativity more accessible to everyone.

Rolling out gradually

The gradual rollout of this feature means some free users might already have access to it. As more people begin to experiment with DALL-E 3, the new capability is likely to democratize creative image generation, making it easier for everyone to bring their ideas to life, even without a subscription.

Featured image credit: Andrian Valeanu/Unsplash

OpenAI introduced a tool for editing through an interface that enables modifications via text descriptions of the desired changes. Let’s learn how to edit images in DALL-E today!

A new feature allows users to target and modify particular sections of an image on desktop interfaces, employing a selection tool represented by an icon resembling a curving paintbrush. Following selection, users have the option to augment, delete, or refine the chosen segment within the editor’s textbox by inputting commands such as “add flowers.”

This selection functionality is also accessible on the ChatGPT mobile application, where areas can be designated for editing by touch.

To highlight part of the image and make edits to specific parts of the picture on desktop, there’s a new select button depicted as a swooping paintbrush icon. From there, you can add, remove, or enhance the highlighted part in the editor text box by giving prompts like, “add flowers.” You can also use the select tool the ChatGPT mobile app and highlight areas with your finger.

-OpenAI

Editing images in DALL-E step by step

• Let’s try it out ourselves. First enter a prompt to create an image.

We said: “Generate me an image of a realistic cute dog.”

The output:

• To open the dialogue box, click on the generated image.
• Then, click on the pen icon located on the upper right part.

• Select the are you want to edit.

• After selecting, enter a prompt to edit the image.

Our prompt: “Add teeth.”

The output:

At least it works…

The outcome isn’t exactly as anticipated, but we can take comfort in knowing that the feature works. Previously, to achieve a specific image outcome, users were required to adjust or completely redo their text inputs, a method that was not always successful. The current editor interface introduces the capability for users to precisely alter images. This is done by choosing a part of the image they wish to modify and detailing the desired edits directly within the conversation.

Featured image credit: Kerem Gülen/DALL-E 3

Have you heard about the news of the MS Paint AI Cocreator? Microsoft has launched its new tool with DALL-E 3 capabilities and it has already caused huge excitement among users from all around the world. There are some limitations and some features are not widely available, but the concept is still here. Here is everything you need to know about it!

Microsoft has just made your artistic dreams come true by bringing its Cocreator image-making tool to the Paint app on Windows 11. It’s like having a magic wand for creating images, and the best part is, now everyone can use it! This nifty tool, powered by OpenAI’s DALL-E 3 model, used to be exclusive, but not anymore. Let’s dive into the world of Cocreator and see how it’s changing the game for creative minds.

What is the MS Paint AI Cocreator and why is it special?

Imagine a button in Microsoft Paint that lets you describe an image and boom! You get three options of images matching your description. That’s Cocreator for you. It’s not like other overwhelming AI tools Microsoft has thrown at us; instead, it feels like a thoughtful addition to the Paint family. This is a big deal, signaling a future where creating images might be as easy as using clip art.

Meet DALL-E 3: The power behind Cocreator

Cocreator is not a lone hero; it has a powerful partner called DALL-E 3, an engine created by OpenAI. This engine can turn text descriptions into images, and it’s not new to the scene. You might have encountered it in Bing or Copilot before. When DALL-E 3 joined Copilot, users went crazy for its improved performance. Microsoft learned from that experience and quickly made sure more people could use it without waiting forever. Now, it’s at the core of Cocreator, ready to turn your words into visual masterpieces.

How to use DALL-E 3 (2 free, 1 paid method)

How to use MS Paint AI Cocreator

Excited to try your hand at this artistic revolution? Here’s your guide to stepping into the world of Microsoft Paint Cocreator:

1. Open Microsoft Paint: Find the Cocreator icon and click.
2. Describe Your Image: Use the text box to tell Cocreator what you want to create. The more details, the better!
3. Choose a Style: Pick a style that suits your vision.
4. Hit Create: Watch as Cocreator generates three different images based on your description.
5. Start Creating: Click on your favorite image to make it your canvas and let the creative journey begin.

Managing Cocreator credits

• Sign in: Make sure to sign in with your Microsoft account to use Cocreator. It also helps you keep track of your credits.
• How Credits Work: Each image you generate spends one credit. You start with a cool 50 credits when you join Cocreator.

Use it responsibly: Filters and guidelines

• Content Filtering: Microsoft cares about responsible use. Cocreator has filters to avoid creating anything harmful or offensive.
• Your Responsibility: Remember to use Cocreator respectfully and follow the rules. Don’t create things that might upset or harm others.

Current limits and privacy assurance

• Waitlist: At first, there might be a waitlist. If you’re interested, sign up, and you’ll get an email when you’re in.
• Where It’s Available: Cocreator is only in a few places right now – United States, France, UK, Australia, Canada, Italy, and Germany.
• Language Support: Cocreator speaks English for now.
• Privacy First: Your privacy is a priority. Cocreator uses an online service to create images but doesn’t store them. Your creations stay private.

Get ready to turn your ideas into art with Microsoft Paint Cocreator. It’s like having a personal assistant for your imagination, making creating images as easy as pie!

Featured image credit: Surface/Unsplash

Join the latest sensation sweeping social media: the Disney Pixar AI dog trend, all thanks to groundbreaking AI advancements!

Remember our recent guides on crafting Disney AI posters and movie scripts?

Using those same techniques, you can effortlessly bring to life Disney Pixar-style dog characters. Ready to conjure up your own unique characters with ChatGPT?

Essentials to get started:

• A ChatGPT account (ChatGPT Plus recommended for optimal results)
• Bing Image Creator.
• Or, as an alternative, consider using Midjourney.

Is the Pixar Harry Potter movie real or AI-generated?

Disney Pixar AI dog trend: Generate your own character with DALL-E 3

By adhering to the outlined instructions, you can efficiently generate a Disney AI dog. Within minutes, you’ll witness your conceptual vision materialize:

• First go to ChatGPT.
• Enter the following prompt: “I’d like to generate a dog image in the style of Disney Pixar using DALL-E. Could you please create three distinct dog characters for me? Please name each one and provide a detailed physical description in 40 words.”
• ChatGPT will provide you with 3 different characters, as seen below:

“Baxter:

• Description: Medium-sized golden retriever with big, expressive hazel eyes. A slightly floppy ear on the right. Always has a shiny, blue bandana around his neck. Enthusiastic and always seems to be smiling. Fluffy tail wags constantly.

Lulu:

• Description: Tiny, white Maltese with a pink bow atop her head. Dainty and always appears to be tiptoeing. Large, round blue eyes framed with long lashes. Carries a petite, heart-shaped locket around her neck. Soft, cloud-like fur.

Rusty:

• Description: Sturdy and stout bulldog with a brindle coat. Has droopy, dark eyes and an underbite showing two bottom teeth. Wears a studded, leather collar. A small scar on his left eyebrow. Loyal demeanor with a slow, deliberate walk.“

• Now it’s time to generate the images! For the sake of this guide, we will choose “Lulu.”

There are two ways to do it: ChatGPT Plus or Bing Image Creator

ChatGPT Plus

With ChatGPT Plus, you have integrated access to DALL-E 3, enabling seamless image generation directly within ChatGPT.

• Go to ChatGPT.
• Open a new chat and select “DALL-E 3.”

Enter your prompt, ours is:

“Generate Lulu. Imagine her as a dog from a Disney Pixar movie. Place her in a Disney-style movie scene.

Lulu: A tiny, white Maltese with a pink bow atop her head. She is dainty and always appears to be tiptoeing. She has large, round blue eyes framed by long lashes and carries a petite heart-shaped locket around her neck. Her fur is soft and cloud-like.“

The result:

Bing Image Creator

With Bing Image Creator, you can take advantage of free credits to generate images using DALL-E 3.

• Visit the provided link.
• Log in using your Microsoft account.
• Input the same prompt to start generating your image.

The result:

Creating DALL-E 3 and Midjourney prompts for characters, logos, etc. is very easy with ChatGPT.

If you opt for Midjourney, you can also check out our guide on how to use Midjourney on Discord. If you want to dive even deeper, these are the Midjourney prompt commands and parameters that you need to learn ASAP.

Featured image credit: Kerem Gülen/DALL-E 3

If you are an old Midjourney fan like us and want to learn how to use DALL-E 3 on ChatGPT or Bing Chat, we are here to help!

OpenAI and Microsoft are making strides in the AI image generation nowadays. After OpenAI released DALL-E 3 for ChatGPT Plus and Enterprise, Microsoft was not too late to join the party by integrating it to the Bing Chat.

For those who might not be in the loop, OpenAI is a leading research organization that has consistently pushed the boundaries of AI advancements. DALL-E is one of its remarkable creations, a generative AI model designed to craft images based on textual prompts. Essentially, it’s a neural network with the capability to produce images in a plethora of styles.

In the competitive landscape, DALL-E 3 faces stiff competition. Names like Midjourney and Stable Diffusion are also vying for attention in the AI image generation arena. Additionally, Google’s Search Generative Experience, which is currently available in a limited number of countries, is making significant inroads in the domain.

However, what sets DALL-E 3 apart is its seamless integration with platforms like Bing and ChatGPT. This integration marks a pivotal moment, bridging the divide between intricate AI tools and the general internet populace.

Comparison: DALL-E 3 vs Midjourney

How to use DALL-E 3 in ChatGPT?

In order to use DALL-E 3 in ChatGPT you need a Plus or Enterprise account. Then, the rest is very easy. Follow these steps:

• Go to ChatGPT or just click on this link.

• Click on “Log in.”

• Enter your credentials.
• Open a new chat, by clicking the relevant button located in the upper right corner.
• When you hover your mouse on top of “GPT-4” you’ll notice a drop-down menu. Select “DALL-E 3” from that menu and you are good to go.

• Now it’s time to generate some images, enter your prompt!
• For the sake of this guide, we tried the following prompt: “A retro TV commercial scene in pop art style, 16:9 aspect ratio”

• As you can see our AI-generated images are ready! We loved the third one, you can check it out here:

How to use DALL-E 3 in Bing Chat?

Just follow these steps:

• Open Microsoft Edge.

• Click on the “+” icon, located on the right pane.
• Activate “Image Creator.”

• Now open the tool by clicking on its icon.
• Enter your prompt. Let’s try the same prompt here: “A retro TV commercial scene in pop art style, 16:9 aspect ratio”

• Unfortunately, Bing Chat version of the DALL-E 3 wasn’t able to give the image in 16:9 aspect ratio, but hey, we’ll take that:

How to use DALL-E 3 in Bing Image Creator?

There’s actually a third way. You can try DALL-E 3 now with Bing Image Creator.

You can directly go to the Bing Image Creator and generate your images there.

• Go to this link.
• Log in with your Microsoft account.
• Enter your prompt.
• Let’s try the same prompt again: “A retro TV commercial scene in pop art style, 16:9 aspect ratio”

• Again, the aspect ratio didn’t work here too. But images are more than fine:

Final words

Exploring the capabilities of DALL-E 3 across various platforms can unlock a world of creative potential. Whether you’re a professional seeking innovative solutions or a curious individual eager to dive into the realm of AI-driven artistry, mastering DALL-E 3 can be a game-changer. These three methods offer just a glimpse into its vast potential. Embracing this technology not only enhances your creative toolkit but also positions you at the forefront of AI advancements. Don’t miss out on this opportunity, learn how to use DALL-E 3 immediately!

Bing’s collaboration with OpenAI’s DALL-E 3 is a testament to the ever-evolving synergy between search engines and AI-driven creativity. No longer confined to the realms of tech enthusiasts and professionals, the capabilities of DALL-E 3 are now accessible to all, free of charge, via Bing Image Creator.

But what if we told you that you could harness the power of this cutting-edge technology without spending a dime? Yes, you read that right! OpenAI has made DALL-E 3 accessible for free through the Bing Image Creator. This article delves into the intricacies of DALL-E 3 and guides you on how to utilize it via Bing.

What is DALL-E 3?

DALL-E 3 is not just another AI tool; it’s a revolution in the world of image generation. Building upon the foundation laid by its predecessors, DALL-E and DALL-E 2, this latest model brings a plethora of enhancements to the table.

Understanding its superiority

At its core, DALL-E 3 has been meticulously crafted to grasp a significantly higher degree of nuance and detail. This translates to an ability to turn abstract ideas and prompts into exceptionally accurate images. Whether you’re thinking of a surreal landscape or a futuristic gadget, DALL-E 3 can bring your vision to life with an accuracy that was previously deemed unattainable.

DALL-E 3 vs DALL-E 2

While DALL-E and DALL-E 2 were commendable in their own right, DALL-E 3 takes the cake with its advanced features. Even when presented with the same prompt, the images generated by DALL-E 3 showcase noticeable improvements over those produced by DALL-E 2. This leap in quality and detail is what sets DALL-E 3 apart in the competitive landscape of AI image generators.

Unique features of DALL-E 3

One of the standout features of DALL-E 3 is its seamless integration with ChatGPT, another groundbreaking AI model developed by OpenAI. This collaboration is not just about combining two technologies; it’s about redefining the user experience.

With ChatGPT as a brainstorming ally, users can refine their image prompts to a granular level. Whether you have a vague idea or a detailed vision, simply converse with ChatGPT. The AI will then generate tailored, detailed prompts, ensuring that DALL-E 3 captures your imagination to the fullest.

While the integration with ChatGPT promises to be a game-changer, users will have to wait a tad bit longer to experience it in its full glory. OpenAI has announced that this integration will be officially rolled out in October 2023. But don’t let the wait deter you! In the meantime, you can still explore the myriad capabilities of DALL-E 3 using the Bing Image Creator online service.

How to access DALL-E 3 for free with Bing?

Accessing DALL-E 3’s prowess is now as simple as logging into a website. To get started, head over to the Bing Image Creator platform. You’ll need a Microsoft account for this, so ensure you’re signed in. The platform is compatible with a range of web browsers, including Microsoft Edge, Google Chrome, Brave, and Firefox, offering flexibility to users.

Once logged in, you might be curious to know if you’ve unlocked the full potential of DALL-E 3. Here’s a quick hack: try inputting a complex text prompt, something that DALL-E 2.5 struggled with. If the generated image is crystal clear and aligns with your prompt, congratulations! You’ve just experienced the magic of DALL-E 3.

Simply:

• Begin by navigating to the Bing Image Creator website using your preferred web browser.
  Once on the platform, you’ll need to authenticate yourself.
• Click on the “Sign In” option and enter your Microsoft account credentials. If you don’t have an account, consider creating one—it’s quick and straightforward.

• With access granted, you’ll find an input section where you can type in your desired prompt. This is your chance to instruct DALL-E 3, so be as imaginative or specific as you wish.

• For those curious about how Bing Image Creator stacks up against other platforms, we conducted a test. After generating an image using our chosen prompt on Bing, we tried the same on Midjourney.

The comparative results are presented below for your perusal:

For a comprehensive comparison of DALL-E 3 and Midjourney we encourage you to read the following article: DALL-E 3 vs Midjourney

Safety and ethical measures

OpenAI has always been at the forefront of responsible AI development, and DALL-E 3 is no exception. The organization has implemented stringent measures to ensure that DALL-E 3 does not generate content that could be deemed violent, adult, or hateful.

Is there a loophole in Midjourney’s NSFW content filter?

OpenAI has equipped DALL-E 3 with features that decline requests related to public figures by name. This not only addresses potential privacy concerns but also ensures that the technology is not misused for creating misleading or harmful content about individuals.

DALL-E 3’s safety protocols don’t stop there. The system has undergone rigorous improvements, especially in areas like the generation of public figures and addressing harmful biases related to visual representation. By collaborating with domain experts and red teamers, OpenAI has fine-tuned this tool to minimize risks associated with propaganda, misinformation, and other potential pitfalls.

In this piece, we will talk about the DALL-E 3 release date. OpenAI, the innovative tech giant, has just unveiled some exciting news for AI enthusiasts and creative minds alike. DALL-E 3, the highly anticipated third iteration of its groundbreaking generative AI visual art platform, is on the horizon.

In this article, we will delve into the details of this upcoming release, including its expected release date and the remarkable features it promises to bring to the table.

DALL-E 3 release date: When to expect?

As of August 20, 2023, the curtain has been lifted, and DALL-E 3 is officially here! However, before you rush to try it out, please note that it is currently only accessible to researchers. The general public will have to wait a little longer, but the good news is that the wait won’t be too extended.

We predict that DALL-E 3 will be released to the public in late Fall 2023. Keep in mind that availability doesn’t necessarily equate to free access. DALL-E operates on a pay-as-you-go (PAYG) business model, which means users will need to pay for tokens to utilize its impressive capabilities.

Comparison: DALL-E 3 vs Midjourney

DALL-E 3 features and more

Now that we have an idea about the Dall-E 3 release date let’s move on to its features. DALL-E 3 marks a significant advancement in the world of AI art generation. For those unfamiliar with its predecessors, DALL-E is an AI system that can transform text prompts into stunning visual art. While the previous versions, DALL-E and DALL-E 2, showcased the potential of AI-generated art, they sometimes struggled with more intricate and nuanced prompts.

The release of DALL-E 3 promises to change the game. OpenAI’s research team has dedicated substantial effort to improving the system’s ability to comprehend the context of prompts. This means that when you provide DALL-E 3 with a description of your artistic vision, it can now grasp the subtleties and finer details, resulting in more accurate and compelling artwork.

Seamless integration with ChatGPT

One of the standout features of DALL-E 3 is its seamless integration with ChatGPT, OpenAI’s renowned chatbot companion. This integration brings AI art creation closer to everyone, regardless of their creative prowess. You no longer need to possess an artistic genius to utilize DALL-E’s capabilities; ChatGPT will be there to assist you.

Here’s how it works: You simply ask ChatGPT to assist you with a prompt, and it will craft a paragraph suitable for DALL-E 3 to work its magic. While DALL-E 3 can still accommodate your unique prompts, the assistance from ChatGPT makes the process of creating AI-generated art more accessible and user-friendly.

Our new text-to-image model, DALL·E 3, can translate nuanced requests into extremely detailed and accurate images.

Coming soon to ChatGPT Plus & Enterprise, which can help you craft amazing prompts to bring your ideas to life:https://t.co/jDXHGNmarT pic.twitter.com/aRWH5giBPL

— OpenAI (@OpenAI) September 20, 2023

In conclusion, DALL-E 3’s impending release is an exciting development in the world of AI art generation. With enhanced contextual understanding, integration with ChatGPT, and a focus on safety, OpenAI is set to empower both seasoned artists and newcomers to explore the limitless possibilities of creative AI. Keep an eye out for DALL-E 3’s public release in late Fall 2023, and get ready to unleash your artistic imagination like never before!

Featured image credit: Andrew Neel/Unsplash

DALL-E 3, the latest version of OpenAI’s ground-breaking generative AI visual art platform, was just announced with groundbreaking features, including ChatGPT integration. While the announcement is quite powerful, we decided to put it in a ring to see how it will be performing.

You’ll initially explore their performance in various aspects like user-friendliness, consistency, visual style, realism, features, community engagement, cost, and beyond. Following that, you’ll delve into a side-by-side image comparison with the same prompt, getting a clearer understanding. This comparison will shed more light on each option’s strengths and unique qualities.

Prepare to embark on an exhilarating journey through the boundless realms of AI-powered creativity as we pit two digital maestros against each other in an electrifying showdown! In one corner, we have the iconic Midjourney, a name that has become synonymous with mind-bending visual imagination. In the other corner, a new challenger with the potential to redefine the AI artistry landscape – DALLE-3! Buckle up, because this clash of AI titans is about to take you on a rollercoaster ride through the future of creativity!

Comparison: DALL-E 3 vs Midjourney

Beyond the artistic flair, here is a quick look for the DALL-E 3 vs Midjourney comparison:

DALL-E 3 was released to ChatGPT Plus and ChatGPT Enterprise users in October, OpenAI has already released some DALL-E 3 creations with their prompt. So, we put the same prompts to Midjourney and see what happens. So, let’s start this fight!

Round 1: Finding the Universe

• Prompt: “An illustration of a human heart made of translucent glass, standing on a pedestal amidst a stormy sea. Rays of sunlight pierce the clouds, illuminating the heart, revealing a tiny universe within. The quote ‘Find the universe within you’ is etched in bold letters across the horizon.”

We have to mention first, as you can see, writing is not Midjourney’s strong side. Because of that, AI tools like Ideogram that are capable of generating images with writing are popular nowadays.

The DALL-E 3 image is very peaceful and serene, and it evokes a sense of connection to the universe. Also, the Midjourney image is more whimsical and playful. However, we have a writing mistake there. Despite their differences, both images are visually appealing and thought-provoking. They both invite us to reflect on our place in the world and our connection to something larger than ourselves.

• The decision: DALL-E 3 wins this round with its flawless generation.

Round 2: Where is the best place to watch the sunset?

• Prompt: “A modern architectural building with large glass windows, situated on a cliff overlooking a serene ocean at sunset.”

Despite their differences, both images are beautiful and evocative. They both capture the essence of living in close proximity to nature. Although we have a clear view of the sunset at DALLE-3, we have to admit that Midjourney’s “sunset vibing” is worth the mention.

• The decision: Midjourney wins.

Round 3: Hail the potato kings!

• Prompt: “Tiny potato kings wearing majestic crowns, sitting on thrones, overseeing their vast potato kingdom filled with potato subjects and potato castles.”
  

Both generations have failed at the same topic. According to the prompt, we need to have multiple thrones. But, in DALL-E 3 generation, there is no throne while in Midjourney image we have at least one.

• The decision: Although DALL-E 3 potatoes are much more like potatoes, we can see at least everything mentioned in the Midjourney image. So, Midjourney wins.

Round 4: The porcelain lady

• Prompt: “A middle-aged woman of Asian descent, her dark hair streaked with silver, appears fractured and splintered, intricately embedded within a sea of broken porcelain. The porcelain glistens with splatter paint patterns in a harmonious blend of glossy and matte blues, greens, oranges, and reds, capturing her dance in a surreal juxtaposition of movement and stillness. Her skin tone, a light hue like the porcelain, adds an almost mystical quality to her form.”
  

The Midjourney generation’s realism is at peak level at we love it! However, we can’t say that there is “a sea of broken porcelain” in that image. While in DALL-E 3 generation, we clearly understand the porcelain touch.

• The decision: DALL-E 3 wins.

Round 5: Let’s dance!

• Prompt: “A 2D animation of a folk music band composed of anthropomorphic autumn leaves, each playing traditional bluegrass instruments, amidst a rustic forest setting dappled with the soft light of a harvest moon.”
  

We have a clear winner there. Although Midjourney’s generation is well presented, there are no autumn leaves to make music.

• The decision: DALL-E 3 wins.

Round 6: The chair

• Prompt: “Photo of a lychee-inspired spherical chair, with a bumpy white exterior and plush interior, set against a tropical wallpaper.”
  

Yes, you probably would choose Midjourney if you want to set it as wallpaper. However, in this comparison, prompt accuracy matters.

• The decision: DALL-E 3 wins.

Round 7: Dancer’s desire

• Prompt: “In front of a deep black backdrop, a figure of middle years, her Tongan skin rich and glowing, is captured mid-twirl, her curly hair flowing like a storm behind her. Her attire resembles a whirlwind of marble and porcelain fragments. Illuminated by the gleam of scattered porcelain shards, creating a dreamlike atmosphere, the dancer manages to appear fragmented, yet maintains a harmonious and fluid form.”

DALL-E 3 almost got knocked out despite its admirable effort! In the Midjourney image, we can see every prompt detail, but better.

• The decision: Midjourney wins.

Round 8: Let’s go to the beach and find the “right” hermit

• Prompt: “Close-up photograph of a hermit crab nestled in wet sand, with sea foam nearby and the details of its shell and texture of the sand accentuated.”
  

In the end, we have to make a close call. Both of the images are well-represented and parallel to the prompt. To decide fairly, we have to admit that we Googled the hermit crab, and it seems like DALL-E 3’s biology is better than the Midjourney. The DALL-E 3 image has an appearance more similar to the real hermit.

• The decision: DALL-E 3 wins.

DALL-E 3: 5, Midjourney: 3

So, we have a winner! Although all of the Midjourney generations were well represented and visually rich, the DALL-E 3 generations were more accurate to the prompt. Because of that, DALL-E 3 deserves the win.

However, we have to mention that these DALL-E 3 generations are specially prepared for the announcement, and they are most likely the best version of themself. While we generated Midjourney images, we took the first versions, to be fair. So, for a final decision, we need to wait for the DALL-E 3’s final release and test it again!

So, is DALL-E 3 as good as Midjourney?

The assessment of whether DALL-E 3 is as good as Midjourney depends on what you looking for. In the comparison based on prompt-generated images, DALL-E 3 won in terms of prompt accuracy, securing victories in five out of eight rounds.

DALL-E 3 demonstrated strengths in generating realistic, accurate images aligned closely with the specified prompts. Its integration with ChatGPT adds a layer of versatility, allowing users to combine language and visual creativity seamlessly.

On the other hand, Midjourney, an established player in the AI art scene, showcased its strengths in creating whimsical and imaginative visuals. While it may not have consistently matched the prompt details as accurately as DALL-E 3, it won in terms of aesthetic appeal and capturing certain nuances. However, it’s worth noting that the comparison used specific prompts and criteria, and different evaluations may arise based on alternative scenarios or criteria.

Ultimately, the evaluation depends on the specific requirements and preferences of the user. If prompt accuracy and simplicity are prioritized, DALL-E 3 may be considered superior based on the provided comparison. However, if a more advanced features and visually rich output is desired, Midjourney might be preferred.

What is the best free AI art generator?

AI-powered art generators were free, each with unique strengths and styles. Some popular ones included:

• Stable Diffusion AI
• WOMBO Dream
• NightCafe
• Meitu AI Art
• Jasper Art
• Artbreeder
• Runway ML

We reviewed all! Check out them and find the perfect fit for you!

Special thanks to Kerem Gülen for generating Midjourney images for this article.

Featured image credit: Google DeepMind/Pexels

DALL-E 3 is finally out, and it is definitely better than its predecessor, according to the announcement made by OpenAI. Below you will find all the details you need to know about the new model!

OpenAI has just unveiled DALL-E 3, the third iteration of its groundbreaking generative AI visual art platform. This new release brings exciting enhancements to the DALL-E experience, including improved contextual understanding, seamless integration with ChatGPT, and robust safety measures. In this article, we’ll explore how to use DALL-E 3, its integration with ChatGPT, and the safety precautions OpenAI has taken to ensure responsible AI art creation.

Our new text-to-image model, DALL·E 3, can translate nuanced requests into extremely detailed and accurate images.

Coming soon to ChatGPT Plus & Enterprise, which can help you craft amazing prompts to bring your ideas to life:https://t.co/jDXHGNmarT pic.twitter.com/aRWH5giBPL

— OpenAI (@OpenAI) September 20, 2023

Comparison: DALL-E 3 vs Midjourney

DALL-E 3 is out and it is better than ever

Before delving into the latest features of DALL-E 3, let’s briefly revisit what DALL-E is all about. DALL-E is an AI system that transforms text prompts into vivid and imaginative images. Its previous versions, DALL-E and DALL-E 2, showcased the potential of AI-generated art but had some limitations when it came to understanding nuanced prompts.

DALL-E 3 is a significant leap forward in AI art generation. OpenAI researchers have worked tirelessly to enhance the system’s ability to grasp the context of prompts. This means that when you describe your vision to DALL-E 3, it is now better equipped to understand the subtleties and details you provide.

ChatGPT integration

One of the standout features of DALL-E 3 is its integration with ChatGPT, OpenAI’s chatbot companion. This integration simplifies the art creation process, making it accessible to a broader audience. Now, you don’t have to be a creative genius to use DALL-E; you can rely on ChatGPT to generate a suitable prompt for your artwork.

Here’s how it works: You ask ChatGPT to help you with a prompt, and it will craft a paragraph that DALL-E 3 can use to generate your artwork. While DALL-E 3 can still accommodate your unique prompts, ChatGPT’s assistance makes AI art creation more approachable for everyone.

Dall-E 3 accessibility and release date

The eagerly awaited DALL-E 3 is set to be initially rolled out to ChatGPT Plus and ChatGPT Enterprise users in October. Following this, research labs and API services will gain access during the fall season. While OpenAI plans a staggered release for DALL-E 3, they have not yet disclosed a specific date for a free public version.

OpenAI is deeply committed to ensuring the responsible use of DALL-E 3. To this end, the company has invested substantial effort in developing robust safety measures. OpenAI collaborated with external red teamers, experts who intentionally try to push the system’s boundaries to test its safety. These measures include input classifiers, which help the language model ignore certain words to avoid explicit or violent prompts.

also, the video we made for dalle 3 is SO CUTE: pic.twitter.com/k1FOFTOsU5

— Sam Altman (@sama) September 20, 2023

Importantly, DALL-E 3 is programmed to refrain from creating images of public figures, provided the prompt explicitly mentions a name. While Sandhini Agarwal, a policy researcher at OpenAI, expressed “high confidence” in these safety measures, it’s crucial to remember that the model is not infallible and continues to evolve.

What about copyright issues?

OpenAI is taking proactive steps to respect artists’ rights. In a bid to avoid potential legal issues, artists can opt their creations out of future versions of text-to-image AI models. Artists who own the rights to their images can submit a request for removal via OpenAI’s website. Subsequently, a future version of DALL-E will block results that resemble the artist’s work or style.

In the past, artists have taken legal action against DALL-E competitors, including Stability AI and Midjourney, as well as the art website DeviantArt, for allegedly using their copyrighted work to train text-to-image models.

In conclusion, DALL-E 3 brings a host of exciting features, including enhanced contextual understanding, ChatGPT integration for streamlined prompts, and robust safety measures. OpenAI’s commitment to responsible AI art creation, along with its respect for artistic rights, marks a significant step forward in the world of generative AI art. As we eagerly await its release, the future of AI-assisted creativity looks brighter than ever. For more information, you can visit the official DALL-E page.

Featured image credit: OpenAI