gen‑ai.news
← Back
Image

Edit Image Quality Update

Edit Image Quality Update

Midjourney has released a quality-focused update to its V8.2 edit model, the version that powers the platform's image editing tools. The update targets output quality problems that some users ran into during the previous 24 hours, and the team is asking anyone who hit those issues to try their edits again now that the fix is in place.

The V8.2 edit model is Midjourney's dedicated pipeline for making targeted changes to existing images - adjusting elements, in-painting areas, or applying style and composition tweaks without regenerating an entire scene from scratch. Quality regressions in editing models can be particularly disruptive because they affect work that users are already invested in, rather than fresh generations where a retry is a lower-stakes decision.

Midjourney's communication around the fix is brief and direct, which is consistent with how the team tends to handle incremental model patches - acknowledging the problem, confirming the update, and inviting continued feedback. The note that "more updates" are coming soon suggests this is part of an active development push around the V8 model family rather than a one-off patch.

Users who rely on the edit workflow are encouraged to test their usual tasks and submit feedback through Midjourney's standard channels. Iterative quality improvements like this one tend to benefit from a wide range of user-reported edge cases, so community input at this stage can meaningfully shape how the model continues to develop.

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

Edit Model for V8
Image

Edit Model for V8

Midjourney has begun rolling out an early test of its V8.2 edit model, bringing instruction-based editing, multi-image reference generation, and inpainting to its latest generation pipeline. The update replaces the previous omni-reference system and supports up to four image references at once. It marks a notable expansion of what users can do directly within the Midjourney platform without leaving to third-party tools.

Adobe is adding more AI to Photoshop
Image

Adobe is adding more AI to Photoshop

Adobe is updating Photoshop with a dedicated "AI Assisted Editor" view, currently in beta, that consolidates the app's AI tools into a single toolbar. The update also introduces a "markup" feature that lets users draw directly on an image to guide the AI on what to change - no text prompts required.

Photoshop's new 'Markup' feature lets you draw on images to show what you want
Image

Photoshop's new 'Markup' feature lets you draw on images to show what you want

Adobe Photoshop is adding a new "Markup" tool that lets users sketch directly on an image to guide AI-based generation - communicating intent visually rather than through text prompts alone. The update also brings Lightroom-style controls to Photoshop, a long-requested addition for photographers and retouchers who work across both apps.