The list in brief ↴
1. Best overall: Adobe Photoshop
2. Best for design: Adobe Firefly
3. Best photo realism: Midjourney
4. Easiest to use: DALL-E 2
5. Open-source: Stable Diffusion
6. Best for video: Runway
7. Best free: Craiyon
8. Best 'remixer': ArtBreeder
How to choose
How we test
FAQs
The best AI image generators allow the creation of stunning images from text descriptions. They're controversial, and they continue to evolve at a speed so fast, we don't know exactly where it will take us, but it's hard to deny that thing anyone working in the visual arts needs to know about them, photographers included.
AI capabilities already existed in popular photo editing software like Photoshop, Lightroom and Luminar Neo. But the best AI image generators can create a whole image from scratch, or generate entirely new parts of an image, based only on a text prompt. Most work in a similar way, but some are more reliable, produce more realistic results or have more intuitive interfaces.
We've tested and reviewed the main options to pick out the best AI image generators for different needs, including for working photographers. Below, we compare the pros and cons of each one and suggest who each is more suited for. See the questions section at the bottom to learn more about how AI image generators work or read on to discover the best AI image generators available today.
The Quick List
Best overall
Visit site
The industry-standard tool for image manipulation has text-to-image generative AI capabilities in the form of Generative Fill and Expand. We think it's the most practical and useful option for photographers who want to use generative AI in their workflow for editing or compositing.
Read more below
Best overall
Visit site
We think Firefly is the best AI image generator for broader design work. As well as the image generator, there's a vector recolour tool, a text effect generator and more. It's trained on rights-free images, making it less controversial, and it integrates well into design workflows.
Read more below
Best realism
Visit site
to generate images from scratch using AI, Midjourney has been leading the pack for a while in terms of photorealism. Its latest iteration, Midjourney V6, is even more powerful, with stunning detail, convincing lighting and reliable prompt interpretation. It can even handle text.
Read more below
Easiest to use
Visit site
AI image generators can feel unfamiliar, but DALL-E is super easy to use. It has a clean interface and a limited number of tools, which means it takes no time to get to know how it works. And if you need help crafting your prompts, there's ChatGPT integration to provide assistance.
Read more below
Open-source
Visit site
Stable Diffusion is open-source and the best generative AI model that you can use completely for free – if you put in the effort needed to run it directly, that is. It's not massively complicated to do that, but it does require a little bit more effort.
Read more below
Best for video
Visit site
AI video generation is not quite as advanced as image generation, but it's developing fast and Runway AI is one of those making that happen. Its motion brush tool can be used to animate still images.
Read more below
The best AI image generators in full
Why you can trust Digital Camera World
The best AI image generator for photographers
Specifications
Reasons to buy
Reasons to avoid
You might be surprised to find this photography and digital art stalwart at the top of our list of the best AI image generators, but hear us out. If you're a photographer looking to use generative AI as part of your editing or compositing workflow, we think Photoshop is the most practical and useful tool to use. For a start, you may already have it or be considering it for other parts of your workflow, from making curve adjustments in layers to airbrushing.
Photoshop's generative AI capabilities are powered by Adobe Firefly (see below). They include Generative Fill, which allows you to select an area of an image and replace it with something else by writing a text prompt, and Generative Fill, which allows you to expand a photo beyond its borders – very handy if you wished you'd taken a shot a little wider.
Generative Fill can be used to remove unwanted objects with cleaner and more powerful results than previous methods like Content-Aware Fill, but it can also be used for much more, from retouching to stylising an image, changing backgrounds and adding completely new elements for those leaning more towards the digital art side of photography.
Photoshop may not be a fully fledged AI image generator, but we have found these generative AI art tools to be genuinely for photo editing, potentially saving hours of work for people who make digital collages or composite images. Best of all, it has dozens of other tools for image editing. When you're a subscriber you automatically get access to updates, and we expect Adobe will be introducing more Generative AI tools in the future.
Of course, it's that monthly subscription that's also the main downside to Photoshop. Using the generative AI features also costs what Adobe calls 'generative credits'. You get a certain number of these included every month with your subscription, and you can buy more. You can still use the tools when your credits run out, but generations will run more slowly
Read our full Photoshop review for more details.
The best AI image generator for design
02. Adobe Firefly
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
Photoshop's generative AI tools are powered by Firefly, and if you take out a Creative Cloud All-Apps subscription, you get full access to both. Firefly is actually free for all to try, although non-subscribers are limited to just 25 free monthly generative credits, enough for just 25 generations.
Firefly has a fully fledged image generator, but also has a wide range of other generators that can be used to recolour vectors, create text effects or convert 3D images to 2D, and more are in development. The results I've for with it suggest that the AI image generator itself is not quite up there with Midjourney, perhaps because it has been trained on fewer images, but image quality and reliability improved massively with the update to a new model in mid-2023.
Adobe's been promoting Firefly as the first 'ethical' AI image generator. That's because it's only trained on images in the Adobe Stock library, where the contributors have allowed them to be studied, and content in the public domain. Thus Adobe has sidestepped any claims that it's infringing people's copyright. That should reassure some business users that they won't get sued for using it (Adobe even promises to indemnify against this for Enterprise users).
Another part of Firefly's special sauce is that it integrates nicely with Creative Cloud tools such as Photoshop, Adobe Express and Adobe Illustrator, where more AI tools are available. That said, you'll need a Creative Cloud subscription to take advantage of all that. For more details, see our article on How to make Firefly work for you.
The best AI image generator for photorealism
3. Midjourney
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
Just over a year ago, we found that Midjourney had a more limited range than other AI image generators we had tried, but that has changed rapidly. Nowadays, it's the tool responsible for many of the AI images that go viral on line because they're so convincing. The pope in a puffer coat? That was Midjourney.
I've found that the latest model, Midjourney V6, is even more powerful, capable of stunning detail in skin and hair, more reliable interpretation of text prompts and much, much better handling of text. Any writing used to be rendered as nonsense. Now, it's possible to even intentionally put phrases of text in images by including them in the prompt. I've found that the generation of human figures is also much more consistent (so no more jokes about AI producing people with six fingers on each hand, or at least not in the foreground). Images can also be produced at higher resolutions using the native upscale tool.
Like with DALL-E 2 and Stable Diffusion, you can also upload your own images to use as references for compositions, but here I find the process to be more convoluted than with other tools. In my opinion, Midjourney still isn't the most intuitive tool for those used to traditional desktop or browser-based apps. Using it on the social platform Discord takes some getting used to, and you have to learn the slash commands needed for different functions. There's also a vast vocabulary of terms and punctuation for prompt crafting. But much of this looks set to change as Midjourney moves to its own dedicated website (at the time of writing, only available to users who have generated more than 10,000 images).
One of the big advantages of Midjourney is its strong community, and it's possible to learn a lot from seeing other people's prompts. On the downside, Midjourney no longer offers a free plan. Basic membership costs $10 a month. That allows you up to three concurrent jobs and 3.5 hours of GPU time a month. Plans go all the way up to the 'Mega plan'. At $120 a month, this gives you up to 12 fast concurrent jobs and 60 hours a month of fast GPU time.
The best AI image generator for ease of use
4. DALL-E 2 / 3
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
OpenAI now has DALL-E 2 and DALL-E 3, and we're placing them both at number 4 in our pick of the best AI image generators because they each have their strengths. DALL-E 3, released in late 2023, is the more powerful model, and we've found that it's capable of producing much more detailed and realistic results.
It also has the benefit of integration with ChatGPT, Open AI's chatbot (In fact, DALL-E 3 is built on ChatGPT, and you need to use ChatGPT to access it. This integration means that you can ask ChatGPT for help creating your prompts, using more conversational language. This can allow a novel back-and-forth dialogue through which you speak with ChatGPT asking it to improve the images that were generated. The downside is that it's more expensive though since it requires a monthly subscription to ChatGPT Plus for $20 a month.
DALL-E 2, on the other hand, is not as reliable but remains one of the best AI image generators for people who want to start exploring the technology. It also, at the time of writing, had more editing tools than DALL-E 3 while still having a very clean, intuitive UI. DALLE-2's text-to-image generator may be a little too limited if you want more control – there's no option to change the size or the aspect ratio of the 1024x1024 canvas, it can't render text successfully and there's no option to add a negative prompt (see Stable Diffusion below). On the other hand, the inpainting and outpainting editing features are among the most advanced.
The former can allow you to paint over part of an image and have the AI generate something else in its place. The latter allows images to be "uncropped", expanding the picture beyond the original frame. This could even be useful for photographers who cropped an image too far or didn't have a wide enough lens to capture the ideal composition.
DALL-E 2 is no longer free, but you get enough free credits to start with to be able to get a decent idea of how it works and what it can do. After that, you get 15 free credits each month. They don't go far but at least let you continue to experiment. More credits are fairly affordable to buy – just bear in mind that you're likely to generate a lot of images that you don't want along the way.
The best open-source AI image generator
5. Stable Diffusion
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
The best AI image generator that you can use for free is Stable Diffusion. However, it requires a bit of technical knowhow to do so. As an open-source program, the code is freely available on Github, which has made it a hit with developers looking to incorporate AI image generation into their own apps. If you have no idea what to do with the code, you can also run Stable Diffusion for free via Google collabs (you'll need to click 'Connect', and then click play on 'install the dependencies' and on 'run the app').
You can avoid this hassle by using Stable Diffusion via Stability AI's web app, DreamStudio, which is almost as clean and intuitive as DALL-E 2 (but like DALL-E 2, it requires you to buy credits). In either case, we found that Stable Diffusion is very close to DALL-E 2 in terms of the range of image styles it can produce, and perhaps even has the edge when it comes to photorealism.
It also offers more control than DALL-E 2 provides, with a flexible aspect ratio, the ability to upscale resolution to 2048x2048 and the option to add a negative prompt specifying what you don't want to appear in the image. You can also set the seed, a number that controls the randomness of a generation, which means it's possible to create the same image again when using the same prompt (other generators can produce totally different results each time even if you use the same prompt).
We were also impressed by the depth-to-image tool, which can infer the depth in a composition of an existing image and transfer it to a new creation. If you're prepared to take the time to work things out and learn some new terminology along the way, Stable Diffusion is the most flexible AI image generator available.
If you use it in DreamStudio, it costs $10 for 1,000 credits, which is enough to generate around 5,000 images at default settings (the higher the resolution and number of steps in the generation, the higher the cost).
The best AI video generator
6. Runway AI
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
A lot of AI video generators focus on creating talking head videos for presentations. Runway is the best AI video generator that we've tested that uses generative AI to create all kinds of videos, and it's been advancing very fast. It also allows users to generate images, and also to add movement to images (simply paint over an image with its beta Motion Brush, and it will turn into a motion image).
Runway has a whole range of generative AI tools, including green screen for changing or removing the background, object removal and a tool to replace sections of a video image. However, we've found that a lot of the tools in Runway are not quite so simple to get good results from. We are talking about video here, which is basically many many images, increasing the chances of weirdl and expected artefacts.
We found the image section replacement tool to be particularly hit-and-miss. But for all its quirks, Ruway is a pioneer in this area. There's a strong community and a lot of tutorial videos to help you get up to speed. The free plan is limited. A standard subscription costs $12 per month per user.
The best free basic AI image generator
7. Craiyon
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
The best AI image generator for those who want to learn how the tech works with no fuss and no payment is Craiyon. There's no need to create an account, no need to run any code and no talking to chatbots. Just go to the website, type what you want in the big box, and Craiyon will get to work. It couldn't be any easier.
The downside is that the resulting images can be strange, glitchy and sometimes just plain frightening. Formerly known as DALL-E mini until OpenAI had words, Craiyon has almost become a genre in itself thanks to its tendency to create mangled images, particularly human faces, but that could change. It says its It's working on a better image encoder.
The unreliable results aren't reason to write Craiyon off. We found that it's capable of turning up surprises that look quite reasonable. It's also surprisingly diverse in its output, which could make it an springboard for new ideas. That said, it's features are limited. There's no inpainting or outpainting and no image-to-image generator. The only thing you can do other than create an image from a text prompt is have T-shirts printed with your designs, should that really take your fancy.
The best AI image generator for 'remixing' portraits
8. Artbreeder
Our expert review:
Specifications
Reasons to buy
Reasons to avoid
Artbreeder is a different kind of beast from the best AI image generators we've mentioned so far. It's based on different technology for a start, using generative adversarial network (GAN) models rather than diffusion. But its interface and what it can do are quite different too. It has too distinct tools: Artbreeder Splice and Artbreeder Collage. The former lets you remix – or 'gene edit' – photos, either those that are already on the site or original images of your own.
This tool has some quirks. It can only handle portraits and landscape photos at the moment (support for other types of image is said to be coming), and images need to be very clean and of high resolution. If you upload a photograph to DALL-E 2 or Stable Diffusion, it will look the way you expect it too, at least until you start generating variations. But even clear, high-resolution portrait shots can end up full of artefacts once they're uploaded to Artbreeder. The subject really needs to be well lit, looking face on and have a clean background.
Find a photo that Artbreeder likes, though, and you can make also sorts of tweaks, changing hair length and colour, facial expression, gender and age in portraits or changing the amount of vegetation, water or weather conditions in landscapes. We find it can be a lot of fun to play around with, and you can use it to create amusing transformations of selfies. Some people have found professional uses for it too. The designer Daniel Voshart uploaded photos of busts of Roman emperors to Artbreeder Splice and turned them into photorealistic images that he now sells prints of.
The second tool, Artbreeder Collage, is a text-to-image generator combined with a collage maker. That's as strange as it sounds, but it kind of works, and it's interesting that it doesn't depend only on text like the tools above. You draw or drag and drop shapes and images onto the canvas (which can include photos of your own, which you can upload), and then you type a text prompt. I found it works well for creating images that look like illustrations – I uploaded a photo of a hummingbird, placed it over an image of a river and asked for a Van Gogh painting, and it delivered a clean if rather cartoonish image but clearly a pastiche of Van Gogh's style. Achieving photorealistic results is more difficult.
How to choose the best AI image generator
There are several things to consider to choose the best AI image generator for you. They include what you want to use it for, how much time you want to spend getting set up, what kind of results you expect, whether you're prepared to pay for it and if you accept how it was trained.
If you've never used an AI image generator and want to very quickly see how they work, you can jump into Craiyon immediately and experiment to see how they work. For the best balance between the ease of use and quality of results, however, we'd suggest trying Adobe Firefly or DALL-E, which are capable of producing impressive photorealistic images.
Stable Diffusion is open source and can be used for free, but that requires, takes a little bit more tech knowhow, while Midjourney is very powerful and impressive when it comes to photorealism and also has a strong community to learn from, but it is no longer available for free and its Discord-based UI takes some getting used to.
We think that if you want a guiding hand – and you want to be sure that nobody's copyright was infringed in the process, Adobe's Firefly is the most useful AI image generator for most people. Meanwhile, Photoshop, which has generative AI tools powered by Firefly, is the most useful tool for most photographers.
No AI image generators have a 100% success rate in interpreting the prompts given. The same prompt used in the same image generator will return different results each time (unless you specify the same seed value). Sometimes the results may reflect accurately what you described, at other times they may be way off. This is something to consider when using text-to-image generators that charge for credits, as you're likely to use up a certain amount of generating images that you don't like and don't go on to use.
How we tested the best AI image generators
We used each of the main AI image generators and asked each tool to produce a range of different kinds of images, from illustration to photorealism using text prompts. We compared the quality of results in different styles, the reliability of each generator's interpretation of text prompts and the ease-of-use of their UI. We also tested image-to-image generating tools and editing features where they exist.
The technology is evolving so fast that models can be improved and the features available expand from one month to the next, but these are best AI image generators that we've tested so far.
AI image generators FAQs
How do the best AI image generators work?
AI image generators are based on machine-learning models that have been trained on vast datasets of millions of images and captions to recognise the relationship between images and text. You type in a short text prompt describing what you want to create, and the AI model will attempt to create that image based on the images and captions it's been trained on.
The best AI image generators use diffusion models. They start out from random dots and begin modifying that noise to move towards the final output as they recognise aspects of the image. In some generators, you can choose how many steps you want the model to take, which will influence how long it takes to generate an image.
How do I get the best results from an AI image generator?
Even the best AI image generators can produce terrible results. By nature there's an element of haphazardness to it, since using the same prompt that resulted in a great image one time, won't necessarily give you the same image when you use it again.
Generally, the more information in the prompt the better. A lack of detail tends to produce unimpressive results, while mentioning things like the style of photography and even a brand and model of camera and the focal length of a lens can lead to better results if you're aiming for photorealism. Some people have reported getting great results from DALL-E 2 by using 'Graflex' in prompts.
Finally, even the best AI image generators have many quirks and produce images with strange artefacts you'll want to fix in traditional image editing software. Human figures are particularly prone to contortions, although problems can often be corrected in Photoshop. Another drawback with AI-generated images can be their resolution, particularly if you want to use them at a large size. Some AI image generators have their own upscaling tools, while with others you will need to use other software such as Topaz Gigapixel AI.
Why are the best AI image generators controversial?
There are several reasons that the best AI image generators are causing controversy. One of the main issues is the fear of misuse to create violent, abusive or pornographic content, and also the fear that people may try to pass off images generated by AI as real, spreading fake news or defaming people.
There are also big questions about copyright, both whether someone can own the copyright to an image they created using AI and whether it was legal to train AI models on images from trawled from the web without the consent of their original creators. Finally, some people have concerns about what they might mean for the future of jobs in some creative sectors.
You might also like: