Midjourney

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Amid intensifying competition in the AI image generation space from the likes of Elon Musk's permissive Grok-2 (powered by Black Forest Labs' open source Flux.1 model), one of the leaders is stepping up its game. Midjourney, which is hailed by many AI artists and designers as the preeminent and highest quality AI image generator, last night unveiled a new, updated version of its website containing a new editor interface that unifies various existing features such as inpainting (repainting parts of an image with new AI generated visuals using text prompts), outpaining/canvas extension (stretching the boundaries of the image in different directions and filling the new space with new AI visuals), and more into a single view. Watch a video of how to use the new menu from Midjourney below: Furthermore, the new web editor contains a new virtual "brush"-like tool for inpainting, replacing the previous square selector and lasso tools and allowing for more precision when it comes to using AI to edit parts of a prior generated image. The new web editor is now live and available to all users who have created at least 10 images on the platform. Users can access this tool by visiting midjourney.com/imagine. Previously, these features were accessible to Midjourney users on the web nested under more disparate menus. The goal, according to a Discord message sent from Midjourney CEO David Holz, is to make editing AI generations easier and more seamless. As Holz stated: "We think this makes editing your MJ images way more seamless than before and is a huge step forward." Indeed, early reactions from users are largely positive: More platform updates In addition to the web editor, Midjourney has introduced another feature aimed at improving communication between its web and Discord communities. Messages sent in certain Web Rooms are now mirrored in corresponding Discord channels and vice versa. This integration ensures that users across both platforms can stay in sync, regardless of where they choose to interact. The rooms with message mirroring include prompt-craft, general-1, and a special superuser room for those who have created more than 1,000 images. Coming at a contentious time for Midjourney and AI art generally The release of the new web editor and the message mirroring feature highlights Midjourney's commitment to continually enhancing the tools and community experiences it offers to its users, even as it faces down a class-action lawsuit from a group of artists accusing the startup of copyright violations for allegedly training en masse on their (and many other) copyrighted images without permission. Last week, the judge in that case denied Midjourney and other AI generator company defendants' bids to have the case dismissed and it is now proceeding toward discovery, which should allow lawyers for the artist plaintiffs who are suing to be able to peer through internal documents of the AI companies and reveal more about their training practices and datasets to the public. Holz also expressed gratitude for the community's patience during the development process and encouraged users to explore the new capabilities provided by the editor. As Midjourney continues to innovate and expand its platform, users can expect more updates and features aimed at improving the overall creative process and fostering a more connected community.

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More After being confined to Discord for much of its first few years and then, in the last year, an "alpha" website for users who had generated a certain number of images, Midjourney, the hit AI image generation service and company, is now opening its website to any users -- with limited free trials even for those not already signed up. To celebrate the launch of this new feature, Midjourney is offering temporary free trials that allow users to generate approximately 25 images. This initiative provides an opportunity for both new and existing users to explore the capabilities of the platform without an immediate financial commitment. It also comes as Midjourney -- considered by many early AI adopters to be the highest quality, "gold standard" of AI text-to-image generation and AI image editing -- faces increasing competition from the likes of Elon Musk's xAI and it Grok 2 (powered by Black Forest Labs' Flux.1 AI model) and the new Ideogram 2 image generator launched today. It's also facing a lawsuit from artists who accuse it of violating their copyright by training on copyrighted works without permission or compensation. How to get started use Midjourney on the web For new users, signing up is a straightforward process, with options to register using either a Google account or a Discord account. This dual sign-up method aims to streamline the onboarding process, catering to a wider range of users. This marks a significant step in making the platform more accessible to a broader audience. Once signed in, the user can create images in sets of 4 by typing in text prompts and descriptions of what they wish to see generated in the text box at the top reading: "What will you imagine?" They can also adjust settings by clicking the box with nobs to the right to bring up a pop-over menu where they can control image aspect ratio and use slider bars to control the degree of stylization (how heavily a particular style is applied), weirdness (the randomness of generation), and variety (how much each of the four images generated per set will vary from one another). On the left side of the website is another column allowing users to navigate to different sections of the site beyond the image creator and editor, including an "Organize" tab for viewing all the user's previously generated images in a photo-like roll, as well as a "Chat" tab for discussing image generations with other users. How existing users can log into Midjourney's website and merge accounts While users can now create images on the web, Midjourney advises existing users to sign in using their Discord accounts if they wish to maintain a history of the images they previously generated on Discord. Additionally, the platform offers the option to merge Discord and Google accounts under the "account" tab. This feature ensures that users can sign in using either account type in the future, providing more flexibility and convenience. Midjourney's decision to open up web-based image creation and offer free trials is expected to attract a diverse range of users, from casual creators to more serious artists, enhancing the platform's user base and engagement.

Digital Trends may earn a commission when you buy through links on our site. Why trust us? Midjourney CEO David Holz announced via Discord on Wednesday that the AI image generator will finally be available to all users, not just paying subscribers, through its website. The text-to-image generator made its debut in 2022 and was originally hosted on a Discord server. The company developed and launched a website last year that mirrored the Discord bot's functionality, though it was originally reserved for users who had already generated at least 10,000 images through the bot. As of now, anybody can give Midjourney a try by visiting its website. You will need either a Discord or Google account in order to sign up. Recommended Videos While you will be able to try the image generator for free, you will not be able to use it in perpetuity. The company is instead offering a free trial of 25 images to all users. Once you work through those 25 freebies, you'll have to sign up for one of Midjourney's paying subscription packages. The $10/month Basic plan starts off with 3.3 hours of GPU time monthly and up to three image generations running concurrently, and goes up from there until you hit the $120/month Mega plan that offers 60 hours per month of Fast GPU time, unlimited hours of "Relax" GPU access, and the ability to generate up to 15 images at the same time. The Midjourney web experience is now open to everyone. We're also temporarily turning on free trials to let you check it out. Have fun! pic.twitter.com/rcmP0UD8PV — Midjourney (@midjourney) August 21, 2024 This news comes barely a week after the company had rolled out its unified web editor in mid-August. While the website originally offered its users a slightly shallower learning curve compared to Discord, its user interface still proved a challenge with popular and often-used tools spread across multiple menus and submenus. The new web editor condensed those menus into a more streamlined process enabling users to more seamlessly switch between various functions like expanding and auto-filling an image's canvas, adding new assets to an image, or even manipulating existing elements.

Why you can trust TechRadar We spend hours testing every product or service we review, so you can be sure you're buying the best. Find out more about how we test. In the world of AI image generation Midjourney is a legend. Launched in July 2022 the platform quickly established itself as a leader in the market. Relying on its own home baked diffusion model based on Stable Diffusion, the service soared in popularity, becoming the best AI image generator we've reviewed. This despite, or maybe because of, its quirky user interface choice. Instead of a flash looking dashboard, we were forced to schlep over to Discord and enter our image prompts behind an /imagine motif, and a long indeterminate queuing system. Positively artisanal. You can check out Midjourney by clicking here. Midjourney offers a Basic plan starting at $10 a month, which provides 3 hours of 'open public' fast image generation via a member gallery. It's a basic plan with few bells and whistles, but it gets the job done. The three other plans start at $30 a month up to $120 and offer faster generation, private images and more generation concurrency. All plans come with some useful editing options. For instance, the platform has a two-click out-painting (zoom out) function and the ability to upscale images. These features allow users to expand their images or improve resolution on demand, making it easier to create high-quality images without needing advanced graphic design skills. If you need more control over your images, you can tweak the prompt with custom zooms and use the image remix and canvas variation buttons. Again using these features can be a little clunky because of the Discord interface, but Midjourney users seem to be a forgiving bunch. As one of the best AI art generators we've tested, a stand-out feature for Midjourney is its distinctive artistic style. The platform excels in delivering images with a unique flair and particular attention to lighting and texture. The results are not just good -- they're often stunning. Typing in a prompt like "a gorgeous tiger sitting on a deserted beach at sunset," for example yields images that are both visually striking and detailed. What sets Midjourney apart from other AI image generators is its ability to add artistry into every image. You can tell an Midjourney creation from a mile away, which is either a good or bad thing depending on your religion. But it does make Midjourney particularly appealing to artists and designers who need AI help, but don't really want to admit it. To use the service, you need to sign up to the Midjourney Discord chat channel. Once logged in, you trigger image generation with the phrase '/imagine' followed by your text prompt. It's not the most user-friendly process, and feels a bit clunky, but it kind of works. This slightly odd interface poses both challenges and opportunities. On one hand it limits the platform's accessibility to those who are familiar with, or willing to learn, how to navigate Discord. On the other, it fosters a community of users who are forced to share their prompts and images, creating a collaborative environment where users can learn from each other. This community aspect is actually quite cool, and inspirational at times. This interface is currently the only way to interact with Midjourney, but there is a promise of a new dashboard arriving soon as highlighted on the showcase home page. Hopefully this new upgrade will also include an easier way to access and manage user accounts. One of the unsung features of Midjourney is its strong community aspect, delivered through the Discord channels. Users share their prompts and generated images in the chat, allowing for a collaborative environment where users can learn from each other's successes and failures. It's a great way for newcomers to learn through feedback, and for experts to act as mentors and help people improve their skills. It's also a double-edged sword of course. It means on the lower plans your generated images are public by default, which could be a drawback for those who value privacy or are creating images for confidential commercial purposes. Spend more money, get more privacy. The Discord community is also the first line of technical support, where users can ask questions, share tips, and troubleshoot common issues. While this peer-group model is useful, it does lack the reliability of a dedicated customer support team. You can get direct support, but it's limited. Thankfully there are some solid tutorials and help FAQs which you can use. Despite its quirks, Midjourney produces exceptional images. However, like any image generator, getting the best results requires trial and error and not a little patience. I found that generating a final image would typically take several attempts, via the Variations button (v1, v2 etc) and/or the Upscale option which allows for out-painting (zoom out) functionality. Surprisingly that is the extent of the editing apart from some limited image variations or crude inpainting options. Learning which prompts yield the best results is like digital gardening. You sow your prompt, observe the results, and tweak or harvest accordingly. This iterative process can be time-consuming, but it's also rewarding. Over time, you develop a better understanding of how to craft prompts that produce the best images in the shortest time. Two years is a long time in AI, and where Midjourney once led a very small pack of image generators back in 2022, now there are significant rivals arriving almost every month. The latest, Flux AI, is a spectacular image service which seems to have grabbed the quality crown - at least for now. This means that in order to keep up, Midjourney is going to have to improve its interface, provide more flexible editing or offer some other meaningful changes. It's a merciless market, as many other image generation services have discovered to their cost. Can the best AI tool for images stay top of the pile? We'll be intrigued to see where the service goes next. Midjourney is a superb veteran in the AI image generation space, delivering images that are more than just good -- they're artistic. The interface, while decidedly old-school and a bit cumbersome, shouldn't deter you if you're willing to navigate through Discord to access the platform's capabilities. Patience and practice will go a long way in getting the best results from this powerful tool. However, it remains to be seen how long this market dominance will continue.

In the rapidly evolving world of AI image generation, finding a cost-effective solution that delivers high-quality results can be a challenge. However, Freepik's AI image generator stands out as a compelling alternative to paid services like Midjourney, offering users the ability to create stunning images without the burden of subscription fees or usage costs. By harnessing the power of Freepik's AI technology, you can unlock a world of creative possibilities while keeping your budget in check. The video below from AI Andy gives us a look at theis free alternative to Midjourney. One of the most significant benefits of using Freepik's AI image generator is the substantial cost savings it offers compared to paid alternatives. With Freepik, you can generate up to 20 images per day completely free of charge, providing a generous allowance for exploring your creative ideas and iterating on designs without worrying about mounting expenses. This cost-effective approach makes Freepik an attractive option for individuals, small businesses, and organizations looking to incorporate AI-generated images into their projects without breaking the bank. Despite being a free service, Freepik's AI image generator does not compromise on the quality of its output. Powered by advanced AI models like Flux and Mystic, Freepik ensures that the images you create meet professional standards, exhibiting sharp details, realistic textures, and coherent compositions. Whether you're designing marketing materials, creating digital art, or visualizing concepts, Freepik's AI-generated images can seamlessly integrate into your projects, maintaining a polished and visually appealing aesthetic. To maximize the potential of Freepik's AI image generator, it's essential to master the art of crafting effective text prompts. By providing clear, descriptive, and specific prompts, you can guide the AI to generate images that align closely with your creative vision. Experiment with different prompt structures, incorporate relevant keywords, and iterate on your prompts to refine the results. With practice and experimentation, you'll develop a keen understanding of how to communicate your ideas to the AI, unlocking a world of creative possibilities. Freepik's AI image generator goes beyond simply creating images from scratch. It offers a suite of advanced tools and features designed to enhance and refine your generated images. Take advantage of capabilities like: These additional features empower you to take your AI-generated images to the next level, ensuring they meet your specific requirements and aesthetic preferences. Freepik's AI image generator seamlessly integrates with the platform's extensive library of designs and mockups, making it easy to incorporate your AI-generated images into a wide range of projects. Whether you're creating social media posts, presentations, websites, or print materials, Freepik provides a user-friendly interface that allows you to drag and drop your images into pre-designed templates, streamlining your workflow and ensuring a cohesive visual experience. Designed with user experience at the forefront, Freepik's AI image generator features an intuitive and accessible interface that caters to users of all skill levels. Beginners can quickly grasp the basics and start generating images with ease, while experienced users can dive deeper into the advanced features and customization options. The platform's user-friendly design ensures that anyone can harness the power of AI image generation, regardless of their technical expertise. In conclusion, Freepik's AI image generator emerges as a innovative alternative to paid AI image generation services. By offering cost-effective, high-quality image creation capabilities, advanced features, and seamless integration with a vast library of designs, Freepik empowers users to unleash their creativity without the constraints of expensive subscriptions. Whether you're a designer, marketer, artist, or simply someone looking to explore the potential of AI image generation, Freepik provides a powerful and accessible platform to bring your visual ideas to life.