Midjourney, a leading AI image generation platform, has launched a powerful new web interface that includes a canvas editor and other user experience improvements. I tested out the new tools and improved interface to see how they streamline the process of creating and refining AI-generated images.
This is a huge step up from the Discord-based image generator that returning users are already familiar with. Thanks to upgraded user interfaceYou now have access to a centralized dashboard to create exceptional works of art, find inspiration and even edit your own images with the power of AI.
Want to know more about the new Midjourney? Keep reading!
A unified web interface
Previously, to use Midjourney, you had to join your Discord server to interact with the AI via text commands.
While the app was powerful enough to serve as a proof of concept, having to rely on an unfamiliar third-party platform was a deterrent for many new users. It was also much less user-friendly, with no drag-and-drop controls, menus, or sliders to make navigation easier.
With its new web interface currently in Alpha, Midjourney has introduced several new quality of life features to improve the end-user experience. Generating creative artwork with the power of AI is now easier than ever, with features such as:
- A unified “Create” tab that lets you generate images from text prompts, with sliders to easily adjust image size, style, and quality.
- A library where you can browse images created by other users for inspiration. You can drag interesting images directly from here into the editor to use as references for your own creations.
- Integrated message mirroring between some Midjourney webrooms and their corresponding Discord channels.
- Faster standard image generation with 25% speed improvement, as well as faster task re-executions.
- Extended access, allowing any user who pays $10/month to access the web UI, not just power users.
The canvas editor is the real star
However, the highlight of the new interface is the canvas-based image editor. Clicking “Editor” on one of your AI-generated images now opens a new tool, which consolidates features like inpainting, outpainting, and image resizing into one powerful view.
With the new AI-powered image editor, you can select specific areas of an image using a brush tool, then change your text prompt to edit only that area.
For example, I had already generated an illustration that featured a stylized representation of a ghost emerging from the forest canopy. By erasing the ghost from the image and then changing the prompt to “scary werewolf,” I was able to transform it into a slightly more insidious version. You can see how the original image compares to the final version. The editor makes this kind of refinement quick and easy.
A Major Upgrade for AI Art Workflows
Midjourney’s web interface and editor are a substantial improvement over the previous Discord-based workflow, putting all the key tools at your disposal to iterate on AI image prompts.
While seasoned artists will still want to use external tools for precise edits, the new built-in editor covers the most important bases. It’s surprisingly good at understanding which areas to edit as you edit the prompt. All of the new additions fit seamlessly into the style and shape of the existing image. Plus, the new UI is sleek and responsive, making the process of generating images feel more like using a modern creative app.
If you’re curious about how to use AI image generation in your creative projects, Midjourney’s new web tools are a great place to start. My only suggestion: I’d like to see more traditional image editing tools integrated into the AI-powered canvas editor for more flexibility.