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.

--sref 2781892103 anime sref while another shows a dense multi-sref prompt stack from earlier Midjourney practice multi-sref prompt.The most consistent creator takeaway is not higher spectacle but thicker scene construction. Dustin Hollywood’s depth examples explicitly calls out composition, lighting, and “DEPTH,” and his surrounding posts back that up with wide shots built around haze, backlight, suspended debris, and layered silhouettes rather than flat poster-style framing. Across the showcase run, V8 outputs move from ritual sci-fi tableaux to confined neon interiors and submerged figures while keeping strong foreground-background separation neon set.
That matters for film-still workflows because the frames read like coverage, not just key art. The shots in part 3 and ECLIPTIC stills suggest blocking, atmosphere, and camera distance choices that can be carried forward into edit and motion treatment.
Dustin Hollywood says the V8 rabbit hole led him to generate “an entirely new film update” for ECLIPTIC, his first AI-made film, and that the next step is animation in CapCut, Dreamina, and Seedance ECLIPTIC remake. That is a concrete creator workflow: lock the script first, rebuild visual language in Midjourney, then hand selected frames to downstream motion tools.
The remake posts show how V8 is being used for worldbuilding, not only single-shot moodboards. One clip names “Dominion” as the supermassive black hole the planet orbits Dominion clip, while later stills add recurring motifs — the oracle, twin suns, tactical figures, floating bodies, and red-lit closeups — that feel like a coherent production pack rather than isolated generations oracle still part 4.
The broader experimentation around V8 is unusually wide. Dustin’s later sets jump from glossy fashion portraits and underwater faces to motel-noir, street-surreal, and desert Americana compositions part 5 part 6. Earlier images in the same run also lean into biotech neon, enclosed cockpit-like spaces, and body-transformation imagery neon set.
Style references still matter, but they are behaving more like starting points than guarantees. Artedeingenio’s anime sref shares a specific code for 80s-90s Japanese cyberpunk anime, while _VVSVS posts a more old-school parameter stack with multiple --sref values, --exp 20, a profile, and --stylize 500 multi-sref prompt. Together they suggest the V8 opportunity is not abandoning saved recipes; it is rerunning them against V8’s deeper staging and seeing which ones survive the transition.
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.
releaseTopview added Seedance 2.0 to Agent V2, pairing multi-scene generation with a storyboard timeline and Business Annual access billed as 365 days of unlimited generations. That moves longform video workflows toward editable sequences instead of stitched clips.
workflowA shared workflow converts GTA-style stills into photoreal images with Nano Banana 2, then animates them in LTX-2.3 Pro 4K using detailed material, skin, vehicle, and camera prompts. Try it for trailer-style previsualization if you want more control at lower cost.
workflowShared Nano Banana 2 workflows now cover turnaround sheets, distinctive facial traits, and photoreal rerenders that keep the framing of a reference image. Use one prompt grammar for concept art, editorial portraits, and animation prep.
releaseLuma launched Uni-1 and says it can reason through prompts while generating images. Creators report stronger composition on first pass for sketch-to-photo, multiview characters, and reference-led scenes, which should cut correction loops.
I went down a rabbit hole with @midjourney v8 and ended generating an entirely new film update for the first film I ever made in AI.. ECLIPTIC. I need to animate it in @capcutapp @dreamina_ai Seedance and then it’s ready! Luckily I already wrote this so it was kinda fun only Show more
Composition, lighting, and most of all DEPTH are exceptional in @midjourney v8 🔥🤌
Part 6 @midjourney v8 🔥✨