Midjourney

Midjourney updated its editor with selected-pixel inpainting, a newer edit model replacing Omni-Reference, revised tile behavior, and an early live preview. The preview is still an early prompt test, while the newer model replaces Omni-Reference in edits.

The workflow uses Midjourney for fighter designs, GPT Image 2.5 for consistent character sheets, and Seedance 2.5 for the arena and 30-second fight. The creator finished the music in Suno and edited the result in CapCut.

Midjourney says its new edit model improves character sheets and character consistency. Company replies say the model replaces Omni and should outperform the prior model.

A creator documented a 10-step fantasy-film workflow that starts with Midjourney references and GPT Image 2 character sheets before using Seedance 2.5 for generation and extension. Additional tools handle the final repair, editing, and music stages.

A creator used Midjourney V8.2 Edit for prompt-directed splash retouching, two-image application shots, and liquid-product composites. One drip shot combined liquid images across three edit steps.

Midjourney updated its V8.2 Edit test model with instruction edits, up to four image references, 2x --hd output, inpainting, and outpainting. Midjourney says the update improves image quality and is seeking feedback.

Midjourney says V8.2 adds instruction-based edits, image inputs, brush inpainting, and outpainting. The tools retain personalization, moodboards, and style references.

Midjourney says V8.2 is now the default image model after a short test cycle, with updates to aesthetics, personalization, and image quality. David Holz singled out personalization as a strength.

AIandDesign released a free Godot port of Terminus Breach for Mac, PC, and Android after moving the bullet-hell game off the web. Posts cite heavy Fable token use, Midjourney backdrops, controller and handheld support, more enemies, VFX, lighting, and difficulty modes.

Creators are turning Midjourney V8.2 stills, character sheets, and storyboard frames into animated sequences in Seedance 2.0, with prompts and shot plans now shared across multiple threads. It matters because Midjourney is being used as the look-dev and planning layer while Seedance handles motion, giving small teams a repeatable image-to-sequence pipeline.

Independent creator tests are stacking up around Midjourney V8.2, with posts comparing --preview outputs and moodboard-driven runs. Early users report stronger images, so creators should keep testing prompt-following and style accuracy before production use.

Midjourney opened V8.2 Preview behind the --preview flag and sped up --sref random draft generation by 24x. Use it to test style directions faster before committing to high-resolution variations.

A published workflow turns Midjourney characters into GPT Image 2 sheets, then uses a long system prompt to generate Seedance audition scenes with role options and voice triggers. Use it to test performance and screen presence before producing full narrative shots.

David Holz posted a midnight improv session filmed inside the future Midjourney Spa and later identified the site as 300 Grant Ave near Union Square. The clip turns this week's spa talk into a real, publicly locatable creative space rather than a distant plan.

Midjourney’s AMA added details to Midjourney Medical: research trials are planned for this year, the spa is targeted for San Francisco by end-2027, and David Holz said the hardware costs are 10x lower than MRI. Current scans use physics-based ultrasound reconstruction, not AI, so watch for whether the rollout timeline and cost claims hold up.

David Holz said he shot and edited the Midjourney Medical launch video himself and built its realtime browser visualization with three.js/WebGL, Claude, and Codex. That turns the hardware reveal into a creator-side production case study, even if the process is still a one-off launch build.

Midjourney unveiled Midjourney Medical, a hardware division centered on a 60-second radiation-free full-body scanner and a San Francisco spa planned for 2027. The reveal shifts Midjourney from image tools toward clinical imaging; watch for whether the company turns the teaser into a regulated product roadmap.

Linus Ekenstam shared a PromptDeck build that rewrites one creative brief into model-specific prompts for Midjourney, Nano Banana Pro, GPT Image 2, Seedance 2, and Kling Omni. The workflow stores optimizer rules in sheets or a database, so teams can edit prompt behavior without redeploying the app.

Midjourney added a V8.1 draft mode that generates 24 lower-resolution images for half the cost of a standard four-image run, with full-res variations available from any hit. The update changes early exploration economics, so creators should use Draft Mode for cheaper ideation before spending on final renders.

Midjourney announced a livestream for its first hardware project on June 17 in San Francisco and teased it in replies. Official hints say it is bigger than an orb, can be entered, and is still a few months from wider availability.

Creators documented a Midjourney-to-Seedance workflow for 15-second fairy-tale and storybook scenes, from frog-to-prince and Cinderella spells to children’s-book animations. Use uploaded character sheets to preserve identity, and compare results against storyboards or Grok Imagine.

David Holz said Midjourney has started sending invites for its first hardware launch event in San Francisco, and the company plans to livestream it. Replies suggest the product is cloud-backed rather than a local compute box, so watch for how Midjourney positions the hardware.

PJ Accetturo published a breakdown of Gossip Goblin's The Patchwright, saying the 20-minute film built on 11 months of prior episodes, tens of thousands of Midjourney images, and mostly Kling animation. Treat it as a continuity-first workflow, not a one-prompt showcase.

A creator partner demo shows Prmptbio turning uploaded Midjourney style references into auto-labeled profile pages and poster exports in Grid, Bento, and Detailed layouts. The tool packages style references into shareable assets without rebuilding showcase pages by hand.

Midjourney V8.1 is reportedly rolling out globally, with stronger moodboard influence, better style adherence and cleaner reruns at fixed seeds. Creators should expect SREF and moodboard libraries to carry more reliably into new image sets.

Midjourney pushed a V8.1 update focused on sharpness and image quality, then enabled the model on its main website and Discord. Creator tests say the biggest gains show up in SREFs, moodboards, HD images and fine detail without upscale; compare your own outputs before migrating.

Creator tests say Midjourney V8.1 renders faster and improves moodboards and lighting, but hand errors and some style outputs still split opinion. Alpha users should compare it against current workflows before upgrading, since the gains depend on the task.

Midjourney shipped V8.1 with native 2K rendering, image prompts restored, a new Describe tool, and faster cheaper modes. Early creator tests suggest it brings back stronger V7-style aesthetics while improving V8 output quality.

Dreamina Seedance 2.0 creators showed Omni Reference swaps that replace characters, cars, and monsters inside existing footage while keeping reflections and motion aligned. Separate demos also chained six stills into one take, used start and end frames for transformations, and added voice-driven talking avatars.

Creators packaged Midjourney looks as reusable SREF products, from Burnt Chrome multi-code blends to neo-noir, retro dark fantasy and cyberpunk presets. The recipes are being framed as commercial-ready style systems for campaigns, posters and character work.

David Holz said a different V8 follow-up is coming soon, while creators posted stranger, more exploratory results from the model. Watch for Midjourney to keep tuning V8 behavior rather than treating the alpha look as final.

Promptsref rebuilt its AI Image Editor so uploads can become cyberpunk or RGB-shift GIFs in one click, then added new SREF guides and an effect tab. The release turns style demos into a reusable post-processing workflow instead of one-off prompt threads.

Creators shared a Midjourney recipe that stacks four SREF codes with --exp 20, --quality 2, and --stylize 500 to get polished surreal close-ups. Use multi-SREF stacking to hold one photographic look more reliably than a single reference code.

Fresh Midjourney sref posts centered on code 3204209964 for dirty-flash 90s snapshots, alongside Matrix-green, warm-glow, and retro-futurist looks. The workflow keeps turning sref into a reusable prompt layer, but results remain highly code- and subject-dependent.

Topaz put Starlight Precise 2.5 inside Astra and highlighted detail restoration, artifact removal, and color cleanup for generated footage. Early creator demos show it as a finishing pass for Midjourney and Grok clips rather than a replacement for generation.

Dustin Hollywood shared the first ECLIPTIC shots featuring Emperor Rho and said the project is being made with Midjourney V8 plus Hailuo. It shows an image-first sci-fi teaser pipeline, though the public material is still limited to early stills and mood shots.

New creator playbooks span sitcom line art, motion-blur cinema, Art Nouveau luxury, neon cyberpunk and rough sketch styles. Reusable srefs are turning into fast moodboards for campaigns, covers and story frames.

Midjourney creators are sharing reusable SREF codes for children's books, retro-film editorials, neon cyberpunk looks and blended vintage illustration styles. Save the strongest codes as presets and mix two or three SREFs when one style feels generic.

Creator posts on March 24 pushed Midjourney V8 hardest on fashion, fine art and moody editorial imagery, while David Holz shared data showing longer prompts are climbing fast. It looks increasingly strong for art-direction-heavy work, but prompt complexity is becoming part of the workflow cost.

Creators are moving from V8 calibration complaints to darker film-still scenes, fashion shots, and worldbuilding tests, with ECLIPTIC remakes showing stronger depth and lighting. Retest saved SREF recipes if you rely on V8 for cinematic ideation.

VVSVS says Midjourney V8 changed how months of calibrated style refs behave, so he cut a 300-world project down to a smaller 30-world pack. If you sell packs or keep internal reference libraries, retest them on V8 before promising consistency.

Creators are turning Midjourney V8 SREF v7 into reusable style packs for cartoons, etchings, retro anime, holographic fantasy, and minimalist branding. Save standout codes now because faster, cheaper moodboards are starting to work like a visual search system.

Hailuo is pushing anime relight tutorials, drag-and-click Light Studio edits, and Midjourney plus Nano Banana combos on its site. Use it when you want faster lookdev passes without rewriting prompts for every lighting change.

Midjourney enabled Relax mode for V8 and rolled out SREF/Moodboards v7 with 4x faster, 4x cheaper styling plus HD, personalization, stylize, and exp support. Test --sv 7 for speed, but keep --sv 6 ready if an older look matters to client work.

MeiGen launched a searchable library of trending X prompts with filters for models like Nano Banana and Midjourney, plus an open dataset you can fork. Build a reusable archive here if your best prompts live in likes and bookmarks.

V8 testers kept praising Midjourney's mood and visual voice while still flagging inaccurate limbs and changed SREF behavior. Run V7 and V8 side by side before moving a client style over.

Prompt libraries kept surfacing high-utility Midjourney SREF looks for comic realism, minimalist doodles, holographic sci-fi, and animation model sheets. Save the codes that match your job type, because they are faster than rebuilding a style from scratch.

Creator tests say V8 is faster and text output is better, but many posts report softer images, profile bleed, mixed prompt adherence, anatomy errors, and heavier moderation. Run V7 versus V8 checks on your core prompts before switching full workflows.

Shared workflows show creators generating flat art with Niji or Midjourney, converting it into polished 3D with Nano Banana 2, then passing frames to Kling for motion. Use it to lock style and composition before animation.

Midjourney opened V8 Alpha on the web with native 2K via --hd, faster renders, better prompt following, and improved quoted text. Test old prompts in --raw and rate outputs carefully, because prompt carryover and pricing are still shifting.