[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-midjourney-web-updates-voice-reuse-prompts-en":3,"article-related-midjourney-web-updates-voice-reuse-prompts-en":30,"series-tools-b73653dc-49c6-4a98-ae45-7a1b879b347f":84},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"b73653dc-49c6-4a98-ae45-7a1b879b347f","midjourney-web-updates-voice-reuse-prompts-en","Midjourney Web Updates let voice reuse prompts","\u003Cp data-speakable=\"summary\">Midjourney’s web update makes voice sessions remember prompts, refs, and settings.\u003C\u002Fp>\u003Cp>I’ve been using Midjourney’s web app long enough to know when a small update actually changes my workflow and when it’s just UI confetti. This one had me annoyed in the usual way: I’d start talking to the app in voice mode, then realize I still needed to reattach the same image prompt, re-pick a style reference, and re-check the sidebar settings like I was rebuilding the whole context from scratch. That’s the part that always felt off. Voice was supposed to feel faster, but it kept acting like a separate room with no memory of what I’d already done.\u003C\u002Fp>\u003Cp>Then I hit the May 27, 2026 \u003Ca href=\"https:\u002F\u002Fupdates.midjourney.com\u002Fweb-updates-5\u002F\">Web Updates post on updates.midjourney.com\u003C\u002Fa>, and the shape of the change clicked. Midjourney isn’t just polishing buttons here. It’s trying to make the web app behave more like one continuous working session, whether I’m typing or speaking. That matters more than it sounds, because the friction in image generation usually isn’t the generation itself. It’s the context juggling before every run.\u003C\u002Fp>\u003Ch2>Voice mode finally stops acting like a blank slate\u003C\u002Fh2>\u003Cblockquote>“When a voice session starts, it has access to your Image Prompts, Style References, sidebar settings, and recent jobs.”\u003C\u002Fblockquote>\u003Cp>What this actually means is that voice input is no longer a disconnected mode. Midjourney is carrying over the stuff I already set up in the web app, so I don’t have to narrate my entire workspace every time I start talking.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780175899902-0qwm.png\" alt=\"Midjourney Web Updates let voice reuse prompts\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>I’ve run into this exact annoyance in other tools too. Voice is supposed to reduce friction, but if it doesn’t inherit state, you spend the first 30 seconds re-establishing context. That’s not faster. That’s just a different keyboard.\u003C\u002Fp>\u003Cp>For me, the practical win is simple: I can start with a visual direction in the sidebar, then switch to voice to iterate without losing the setup. If I’m testing a composition idea, I don’t want to re-say “use the third reference, keep the same moodboard, keep the same aspect ratio” like I’m feeding a machine that forgot its own notes.\u003C\u002Fp>\u003Cp>How to apply it: treat voice as continuation, not a separate workflow. Set your references and sidebar options first, then use voice for the back-and-forth part. If you’re building a team process around Midjourney, document that order. It keeps people from blaming voice when the real issue is that they started speaking before the session had any useful context.\u003C\u002Fp>\u003Cul>\u003Cli>Set image prompts before you enter voice.\u003C\u002Fli>\u003Cli>Use voice for iteration, not for re-describing the whole setup.\u003C\u002Fli>\u003Cli>Assume the session is stateful now, and organize your steps that way.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Tray images persisting across voice is the real quality-of-life fix\u003C\u002Fh2>\u003Cblockquote>“Image Prompts now work from the tray and sidebar. Tray images persist across voice submissions until you remove them.”\u003C\u002Fblockquote>\u003Cp>What this actually means is that Midjourney is finally treating the tray like a working surface instead of a disposable staging area. I can keep the same images attached while I fire off multiple voice prompts, and that matters because most image iteration is not one-and-done. It’s a loop.\u003C\u002Fp>\u003Cp>I used to lose time because I’d make a first pass, then have to stop and reattach the same references before the next pass. Tiny annoyance, sure. But tiny annoyances stack up fast when you’re exploring ten variations of the same idea. This update removes one of those dumb little pauses that breaks momentum.\u003C\u002Fp>\u003Cp>The part I like is that image prompts now work from both the tray and the sidebar. That means I’m not forced into one rigid place to manage references. If I’m moving quickly, I can keep the visual anchors visible and just keep refining.\u003C\u002Fp>\u003Cp>How to apply it: keep your reference images in the tray while you’re exploring a concept, especially if you’re switching between text and voice. Don’t clear them unless you’re intentionally changing direction. If you’re working with a client-facing art direction board, this is the sort of thing that keeps the session readable instead of turning it into a scavenger hunt.\u003C\u002Fp>\u003Cul>\u003Cli>Leave reference images in the tray during iterative runs.\u003C\u002Fli>\u003Cli>Use the sidebar when you want more deliberate control.\u003C\u002Fli>\u003Cli>Only remove tray items when you’re done with that visual direction.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Rerun as HD is the kind of button I wish existed earlier\u003C\u002Fh2>\u003Cblockquote>“A new Rerun as HD button makes it easy to rerun any V8.1 image generated in Standard Definition (SD) as High Definition (HD).”\u003C\u002Fblockquote>\u003Cp>What this actually means is I don’t have to treat SD output like a dead end anymore. If a result is basically right but too soft, I can rerun it as HD instead of rebuilding the prompt from scratch and hoping I land back in the same neighborhood.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780175900507-wfvu.png\" alt=\"Midjourney Web Updates let voice reuse prompts\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>I’ve wasted more time than I want to admit on the classic “this is almost it” problem. The image is right enough to keep, but not right enough to ship. Before a button like this, the fix was usually some mix of prompt tweaking, rerolling, and mild self-delusion. Now Midjourney is giving me a direct path from draft quality to presentation quality.\u003C\u002Fp>\u003Cp>This is especially useful if you use SD for fast exploration. That’s the sane way to work: move quickly first, then sharpen the output once the direction is clear. The new rerun button basically formalizes that pattern.\u003C\u002Fp>\u003Cp>How to apply it: use SD for breadth and HD for polish. Don’t burn time forcing every early idea to be perfect. Generate fast, pick the best direction, then rerun as HD when the composition is already doing what you want. If you’re building a production pipeline, this is the exact kind of split that keeps throughput sane.\u003C\u002Fp>\u003Cp>For reference, Midjourney’s own docs and product pages are still the best place to keep up with format changes around V8.1 and web workflows. I’d also keep an eye on the main \u003Ca href=\"https:\u002F\u002Fwww.midjourney.com\u002F\">Midjourney site\u003C\u002Fa> and the broader \u003Ca href=\"https:\u002F\u002Fdocs.midjourney.com\u002F\">Midjourney docs\u003C\u002Fa> if you’re standardizing this for a team.\u003C\u002Fp>\u003Ch2>Filters and folder counts sound boring until you’re buried in assets\u003C\u002Fh2>\u003Cblockquote>“Folder views on the Create and Organize pages now show a hidden-item count so you can see how much is filtered out.”\u003C\u002Fblockquote>\u003Cp>What this actually means is Midjourney is making the library state less mysterious. If I’ve filtered out a pile of items, I can see that something is hidden instead of wondering whether the folder is actually empty.\u003C\u002Fp>\u003Cp>I’ve lost time in tools that hide too much. You click into a folder, it looks empty, and then you spend a minute checking whether the filter is wrong, the search is too narrow, or the content is gone. A hidden-item count doesn’t sound glamorous, but it cuts straight through that confusion.\u003C\u002Fp>\u003Cp>The filter reset button moving from the bottom to the top is the same kind of fix. It’s a small UI change, but it reduces the number of times I have to scan the whole panel just to undo a filter state. That’s not design poetry. That’s just respecting muscle memory.\u003C\u002Fp>\u003Cp>How to apply it: if you’re organizing a large set of generations, use the hidden-item count as a sanity check before you assume something is missing. When you’re training a team, tell people to reset filters from the top now, not the bottom. Tiny layout changes are exactly where people waste time when they’re moving fast.\u003C\u002Fp>\u003Cul>\u003Cli>Use hidden-item counts to distinguish “filtered out” from “gone.”\u003C\u002Fli>\u003Cli>Reset filters before you start searching for missing work.\u003C\u002Fli>\u003Cli>Teach teammates the new control location so they stop hunting for it.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Mobile web got a cleanup pass, not a fancy rewrite\u003C\u002Fh2>\u003Cblockquote>“On mobile web, the settings menu now groups Profiles, Moodboards, and Liked Styles together. The More Options panel is available in the mobile lightbox.”\u003C\u002Fblockquote>\u003Cp>What this actually means is Midjourney is trying to make the mobile web experience less scattered. Profiles, Moodboards, and Liked Styles belong together conceptually, so grouping them together is the right move.\u003C\u002Fp>\u003Cp>I don’t use mobile web for deep work, but I do use it for quick checks, approvals, and “let me just see what that looks like” moments. In those cases, the problem is never raw capability. It’s navigation. If I have to dig through three areas to find the thing I already know exists, the mobile experience feels heavier than it should.\u003C\u002Fp>\u003Cp>The More Options panel in the mobile lightbox is another one of those practical fixes that matters when you’re away from your desk. It gives you more control without forcing a desktop detour.\u003C\u002Fp>\u003Cp>How to apply it: if your team reviews generations on phones, standardize where people go for profiles, moodboards, and liked styles. Don’t make them rediscover the menu every time. And if you’re the person writing documentation, update your screenshots now, because old mobile UI docs are a special kind of lie.\u003C\u002Fp>\u003Ch2>The bug fixes matter because they remove bad guesses\u003C\u002Fh2>\u003Cblockquote>“Search on the Create and Organize pages now works for signed-in members without an active subscription.”\u003C\u002Fblockquote>\u003Cp>What this actually means is that Midjourney fixed a bunch of failure states that used to make the app feel flaky, even when the real issue was just state handling or permissions.\u003C\u002Fp>\u003Cp>The upload error message now showing the correct 20 MB limit is a perfect example. If a tool tells me the wrong limit, I stop trusting the message and start guessing. Same with failed jobs showing Vary or Upscale buttons that can’t run. That’s not a feature. That’s a trap.\u003C\u002Fp>\u003Cp>I also care about the rate-limit message appearing when an upload is throttled, because silent throttling is one of those bugs that makes people blame themselves. The prompt scrolling fix on the Create page, the Subscribe button no longer getting stuck after navigating back, and the Niji 6 or V6 Personalization profile staying selected all point in the same direction: fewer weird edge cases, fewer moments where the UI lies to you.\u003C\u002Fp>\u003Cp>How to apply it: if you’re using Midjourney in a production setting, test the failure states, not just the happy path. Try search while signed in without a subscription. Try uploads near the size limit. Try back navigation. Tools feel stable when they stop surprising you in the bad states.\u003C\u002Fp>\u003Cp>I’d also keep a simple internal checklist for your own workflow:\u003C\u002Fp>\u003Cul>\u003Cli>Verify upload limits before batching assets.\u003C\u002Fli>\u003Cli>Check that the buttons on failed jobs actually match the job state.\u003C\u002Fli>\u003Cli>Watch for throttling and rate-limit messages instead of retrying blindly.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>What Midjourney is really doing here\u003C\u002Fh2>\u003Cp>This update is not about one flashy feature. It’s about reducing context loss. Voice inherits state. Tray images persist. Filters are more legible. Mobile navigation is less awkward. Even the bug fixes are about making the app stop contradicting itself.\u003C\u002Fp>\u003Cp>That’s the pattern I pay attention to. When a tool starts preserving context properly, my workflow gets less brittle. I spend less time reintroducing information and more time deciding what the image should actually become.\u003C\u002Fp>\u003Cp>If you’re building prompts, templates, or internal tooling around Midjourney, this is the lesson to steal: make the working session persistent. Don’t make people restate what the interface already knows. That’s the difference between a tool that feels fast and a tool that just has a lot of buttons.\u003C\u002Fp>\u003Cp>And honestly, that’s the kind of update I trust. Not because it’s flashy, but because it removes the little paper cuts that keep turning a creative session into admin.\u003C\u002Fp>\u003Ch2>The template you can copy\u003C\u002Fh2>\u003Cpre>\u003Ccode># Midjourney web workflow template for stateful sessions\n\n## Goal\nUse one continuous Midjourney session for text, voice, references, and reruns without rebuilding context.\n\n## Before you start\n1. Open Midjourney web.\n2. Add your Image Prompts to the tray or sidebar.\n3. Set your Style References.\n4. Confirm sidebar settings like aspect ratio, stylization, or any project-specific defaults.\n5. Keep recent jobs visible if you want to iterate from prior outputs.\n\n## Voice workflow\n- Start voice mode only after the visual context is in place.\n- Keep tray images attached across submissions.\n- Use voice to refine, not to restate the whole setup.\n- Remove tray images only when changing directions.\n\n## Iteration workflow\n- Use SD for fast exploration.\n- Pick the strongest composition.\n- Click Rerun as HD for V8.1 images that need cleaner output.\n- Avoid rebuilding the prompt unless the direction itself changed.\n\n## Organization workflow\n- Check hidden-item counts in folder views before assuming assets are missing.\n- Reset filters from the top of the filter bar.\n- Use Create and Organize search to find prior work, even if you are signed in without an active subscription.\n\n## Mobile workflow\n- Find Profiles, Moodboards, and Liked Styles under the grouped settings menu.\n- Use the More Options panel in the mobile lightbox for quick edits.\n\n## Troubleshooting checklist\n- If upload fails, confirm the 20 MB limit.\n- If a job fails, do not rely on Vary or Upscale buttons unless they are actually available.\n- If upload is throttled, wait for the rate-limit message and retry later.\n- If copy actions feel delayed, wait for clipboard confirmation before moving on.\n- If personalization profiles deselect themselves, re-check the selection state before continuing.\n\n## Team note\nDocument the order of operations:\nreferences first, voice second, HD rerun last.\nThat keeps the workflow consistent across desktop and mobile.\n\u003C\u002Fcode>\u003C\u002Fpre>\u003Cp>This template is my own cleanup and workflow version of the Midjourney update, not the original post. The source change log is at \u003Ca href=\"https:\u002F\u002Fupdates.midjourney.com\u002Fweb-updates-5\u002F\">https:\u002F\u002Fupdates.midjourney.com\u002Fweb-updates-5\u002F\u003C\u002Fa>, and anything above that quotes the update text is derivative of Midjourney’s own wording.\u003C\u002Fp>","Midjourney’s web update makes voice sessions remember prompts, refs, and settings, plus adds HD reruns and cleanup fixes.","updates.midjourney.com","https:\u002F\u002Fupdates.midjourney.com\u002Fweb-updates-5\u002F",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780175899902-0qwm.png","tools","en","576656e6-be71-4b41-84a4-c0514700752a",[17,18,19,20,21],"Midjourney","voice mode","image prompts","HD rerun","web app",[23,24,25],"Voice sessions now inherit prompts, refs, settings, and recent jobs.","Tray images persist across voice submissions until removed.","Rerun as HD turns SD drafts into cleaner final outputs.",11,"2026-05-30T21:17:53.721784+00:00","2026-05-30T21:17:53.713+00:00","4fe6287b-d452-4b78-8da6-918c10aefb69",{"tags":31,"relatedLang":43,"relatedPosts":47},[32,34,36,39,41],{"name":17,"slug":33},"midjourney",{"name":20,"slug":35},"hd-rerun",{"name":37,"slug":38},"Web App","web-app",{"name":18,"slug":40},"voice-mode",{"name":19,"slug":42},"image-prompts",{"id":15,"slug":44,"title":45,"language":46},"midjourney-web-updates-voice-reuse-prompts-zh","Midjourney 讓語音接住上下文","zh",[48,54,60,66,72,78],{"id":49,"slug":50,"title":51,"cover_image":52,"image_url":52,"created_at":53,"category":13},"1e0d71a2-19ae-44f4-970b-d27f77ad5a8a","nvidia-lg-ai-collaboration-playbook-en","Nvidia and LG turn AI plans into a playbook","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781056992194-i3tx.png","2026-06-10T02:02:46.922181+00:00",{"id":55,"slug":56,"title":57,"cover_image":58,"image_url":58,"created_at":59,"category":13},"9db77f6f-0d31-4686-86d9-16eb9615633d","ollama-best-free-ai-path-2026-en","Ollama is the best free AI path in 2026 for real work","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781056075632-qzpq.png","2026-06-10T01:47:25.10989+00:00",{"id":61,"slug":62,"title":63,"cover_image":64,"image_url":64,"created_at":65,"category":13},"c12c0470-eb29-4e44-872d-c133a84a1bc8","awesome-production-ml-turns-chaos-into-stack-en","This MLOps list turns chaos into a stack","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781055237524-86fa.png","2026-06-10T01:33:15.495884+00:00",{"id":67,"slug":68,"title":69,"cover_image":70,"image_url":70,"created_at":71,"category":13},"58924f21-83f4-405d-8d9a-4af334e9d030","bentoml-turns-model-serving-into-python-apis-en","BentoML turns model serving into Python APIs","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781054304942-bxxs.png","2026-06-10T01:17:56.721066+00:00",{"id":73,"slug":74,"title":75,"cover_image":76,"image_url":76,"created_at":77,"category":13},"aa96e422-2b01-4480-b4ce-a646be8e0993","magenta-realtime-2-score-inside-daw-en","Magenta RealTime 2 lets you score in the DAW","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781046208039-ksdz.png","2026-06-09T23:02:56.428086+00:00",{"id":79,"slug":80,"title":81,"cover_image":82,"image_url":82,"created_at":83,"category":13},"c79bca38-50b2-4d80-9a48-7f4d1afd051a","open-source-ai-tools-beat-claude-paid-tiers-en","Open-source AI tools beat Claude’s paid tiers on value","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781045269190-a1ow.png","2026-06-09T22:47:20.7972+00:00",[85,90,95,100,105,110,115,120,125,130],{"id":86,"slug":87,"title":88,"created_at":89},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":91,"slug":92,"title":93,"created_at":94},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":96,"slug":97,"title":98,"created_at":99},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":101,"slug":102,"title":103,"created_at":104},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":106,"slug":107,"title":108,"created_at":109},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":111,"slug":112,"title":113,"created_at":114},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":116,"slug":117,"title":118,"created_at":119},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":121,"slug":122,"title":123,"created_at":124},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":126,"slug":127,"title":128,"created_at":129},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":131,"slug":132,"title":133,"created_at":134},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]