gen‑ai.news
← Back
Image

Changelog - 8/20/26

Two weeks after rolling out a significant set of early-stage changes to alpha.midjourney.com, Midjourney has published a new changelog marking the next iteration of that work. The update comes after the team gathered input from thousands of users who tested the alpha builds, with hundreds submitting detailed feedback - ranging from praise to pointed criticism. The willingness to absorb that range of responses appears central to how the team is approaching this development cycle.

The alpha environment functions as Midjourney's public testing ground, where features are intentionally unfinished and subject to rapid change. By opening that process to a broad user base, the company is trading polish for a faster feedback loop - getting real-world signal on what is and is not working before anything reaches the main platform. That approach carries tradeoffs, and the team seems aware that rough edges come with the territory.

While the specific feature changes in this changelog were not fully detailed in the available description, the framing suggests the update addresses usability and interface concerns raised during those two weeks of testing. Midjourney has been steadily rebuilding and expanding its web platform after years of operating primarily through Discord, so changes to the alpha site are likely connected to that broader shift toward a standalone product experience.

For users already active on the alpha, this changelog represents the team closing the loop on an unusually open feedback period. For those watching from the outside, it signals that Midjourney continues to iterate on its web interface at a regular pace, with community input playing a meaningful role in shaping what comes next.

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

Building Agentic Document Intelligence Pipelines: Creating Scientific Figures with AutoFigure

AutoFigure is a toolkit that takes text descriptions and research paper content as input and produces publication-ready scientific figures. A new tutorial from MarkTechPost walks through the full setup process, from configuring an API-backed workflow to exporting styled diagram galleries. The piece is aimed at researchers and developers looking to automate the visual documentation side of document intelligence pipelines.

OpenAI's GPT-Image-2 can now generate images without a background
Image

OpenAI's GPT-Image-2 can now generate images without a background

OpenAI has added transparent background support to its GPT-Image-2 model, available in preview through the API. Rather than removing a background after the fact, the model bakes the alpha channel directly into the generation process. The feature is enabled with a single parameter.

Subtlefakes: Slightly Altered Nonconsensual AI Images Are Taking Over X
Image

Subtlefakes: Slightly Altered Nonconsensual AI Images Are Taking Over X

A growing trend on X involves nonconsensual AI-generated images that have been subtly altered - tweaked just enough to evade automated detection while still being clearly identifiable as depicting real individuals. The technique is making moderation significantly harder and is spreading rapidly across the platform. 404 Media reports on how these so-called "subtlefakes" are changing the landscape of image-based abuse.