gen‑ai.news
← Back
Image

Alpha Changelog - 10/1/26

Midjourney has pushed a batch of updates to its alpha web interface at alpha.midjourney.com, covering three distinct areas: style browsing, image presentation, and parameter management. The additions are incremental but address friction points that users of the web-based workflow have run into since the platform began shifting focus away from Discord toward its own dedicated site.

The most visible change is the addition of style previews directly in the sidebar. Previously, selecting a style required either prior experience with it or a separate test generation to understand what the output would look like. The preview thumbnails let users make a more informed choice before committing a prompt to the queue - a small but meaningful step toward making the interface more self-explanatory for newer users.

The create view now also displays larger images, which makes evaluating results easier without needing to open each one individually. This is particularly relevant for users comparing multiple outputs from a single prompt, where subtle differences in composition or detail can be hard to spot at smaller sizes.

The third addition - setting default parameters at the folder level - adds a layer of organizational control that power users have been working around manually. By assigning defaults to a folder, users can keep consistent settings across a project without re-entering parameters each time. This fits into a broader pattern of Midjourney building out the web platform as a more structured, project-oriented workspace, rather than a simple prompt-and-generate interface.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Image

Pope Leo XIV is not a fan of AI-generated art

Pope Leo XIV has spoken out against AI-generated imagery, arguing that a fundamental difference exists between human art and machine output - one that goes deeper than aesthetics. In a written statement, he contended that algorithms, drawing on the work of countless human creators, cannot replicate what he calls the "spark of humanity." The remarks add a notable philosophical voice to an ongoing debate about the nature and value of AI-generated content.

ChatGPT can now help you virtually try on clothes
Image

ChatGPT can now help you virtually try on clothes

OpenAI has added a virtual try-on feature to ChatGPT, letting users see how clothing looks on them using the platform's latest image generation model. Items that catch a user's eye can be saved for later reference. The feature brings AI-assisted shopping one step closer to a practical everyday tool.