Here’s a look at how generative AI works and what Shutterstock is contributing to this technological breakthrough.
Generative AI is changing the nature of creative work. Now, anyone can type out some thoughtful text, click a button and, within seconds, AI will generate a new image based off of what they wrote.
In general, artificial intelligence can create a wealth and variety of new content nowadays. ChatGPT is already disrupting academia, marketing, and more by writing copy of a fairly decent quality. Meanwhile, AI-based image generators, like Shutterstock’s new AI image generator tool or OpenAI’s DALL-E 2, are creating imagery from text prompts.
All are causing quite a stir on social media, and people are wondering how they can use them in their own work.
Interestingly enough, many Shutterstock customers have already taken an interest in generative AI. In fact, 45% of Shutterstock customers have already used generative AI and 66% want to learn more about it. This suggests that creative work is already undergoing a transformation.
Creative content generated by AI is leading to an explosion of new experiences. It will inspire creative thinkers to try new things. Generative AI can also enhance processes and shorten timelines.
Still, while we may have a good understanding of what generative AI can do, you may wonder how it actually works. Here, we speak to Chris Loy, Shutterstock’s Director of AI Services, to get a better understanding of generative AI’s engineering and capabilities.
Want to get a peek behind the curtain of today’s latest and greatest tech? Keep reading.
What Is Generative AI?
Generative AI is a branch of machine learning focused on creating AI models that learn from pre-existing content, such as images, video files, text, and audio. These models ultimately create new, never-before-seen content on demand.
As previously mentioned, there are many different types of generative models–such as text-to-video or text-to-3D. In this blog post, we’ll focus on text-to-image AI.
From the user experience perspective, text-to-image generative AI looks like this: If you have an idea, enter text that describes it into Shutterstock’s AI image generator tool. Within a few seconds, you will see four images that visualize what you typed.
Not only is this easy to use, but getting started is straightforward and simple. In fact, you can experiment with generating images right now.
What’s Unique About Shutterstock’s Generative AI Tool?
Shutterstock’s new AI image generator is simple to work with and it delivers quality images to end users. “We are bringing a fully fledged suite of tools for content generation (to our customers),” says Loy. “(These tools) lean heavily on our intuitive, easy-to-use products, our end-to-end creative capabilities and, most importantly, our library of licensable stock content.”
“You don’t have to write a super complicated prompt to get good results,” Loy says, when describing the process of using the tool. Trustworthy models, sound data, and a simple interface all lead to quality images in the end.
In order to produce such images, we’ve partnered with OpenAI. They are the creators of DALL-E 2, which powers Shutterstock’s generative AI, and they’re leaders in generating images from natural language descriptions.
Ready to unleash your creativity with the power of AI? Just type a description of something to get started.
AI Image Generator: Create stunning visuals instantly
The AI image generator, at the heart of this partnership, was built using millions of diverse, responsibly sourced visuals. As part of our commitment to responsible AI, we compensate known contributors to AI for licensing revenue associated with AI-generated images on our platform.
You can enter as little as a single word to start generating . . . or get as specific as you’d like! Select styles like digital, photo, or 3D to tell the AI what type of image you’d like it to generate. Using this style picker allows users to quickly and easily sort through ideas they like and dislike, getting them to their ideal results more quickly.
As you edit and refine your text, you’ll see changes to your image results. Once you find one you want to work with, you can save it to a collection or purchase it.
How to Use Generative AI
Right now, you can generate nearly any image you can dream up. Think through what you’d like to create, type your text into the AI image generator, and see what results await. Get started writing your own prompts or visit the tool directly to explore its style picker.
Beyond these current capabilities, this technology will continue to boom in the future.
“The sky is really the limit when it comes to where this technology is likely to grow,” says Loy. “Today, we are launching the ability to type in a text prompt and receive a square, medium-resolution image. That is soon going to be much more.”
Smart editing capabilities, higher resolution images, various aspect ratios, and moving beyond producing just static images are all expected to be a part of the evolution of generative AI’s capabilities.
“As this technology develops in the long term, Shutterstock will find how to bring those capabilities to our customers in ways that allow them to create with confidence, while ensuring that artists and contributors are fairly compensated.”
It’s exciting to learn where this technology will likely go in the near future, but it’s even more exciting to start using it right now. If you’re ready to produce new images using Shutterstock’s AI image generator, you can create at the speed of your imagination today.
Learn AI Basics
Download our free ebook How to Use Generative AI for Real Work: A Practical Guide for Creatives and Marketers. Inside, you’ll get the lastest tips and tricks to help you learn AI basics.
You’ll also learn how a variety of roles, from project managers to designers, can use AI to supplement work and speed up processes.
License this cover image mockup via Login and Login.
