Cracking Midjourney’s Style Explorer + Freepik’s Rise + Higgsfield Prompt Hack

Two tired dads with graying hair accidentally stumble into a killer AI workflow. In this Halloween-season hang, Drew Brucker and Rory Flynn trade Midjourney Office Hours intel (V8, maybe no 7.1), go deep on the Style Explorer/Style Finder with token-level searches, then build a rapid prompt-testing pipeline across Weavy + multiple image models. Somewhere between Scream and Sandstorm, they also unpack Freepik’s new “aggregator” lane and Higgsfield’s Popcorn storyboard—then end by stealing prompts (on purpose) with a Chrome trick.If you’re asking “How do I actually use Midjourney’s Style Explorer to find usable looks?” or “What’s a fast way to test a single prompt across lots of models?”—this one answers both, with receipts.What you’ll learn- Midjourney V8 expectations, edit models, multi-image refs, UI shift (less typing, more visual control)- Token-based Style Explorer searches- Practical permutations (exp, Chaos 5–7), when Draft Mode helps (and when it doesn’t)- Weavy “fan-out” testing: run one prompt through Re-Render/Ideogram/Flux/Mystic/Imagen/Luma/etc.- Freepik as a real workflow hub (collections, templates, brand swaps)- Higgsfield Popcorn: storyboard → video; plus the Chrome “Recreate” move to harvest solid prompt structure#midjourney #midjourneyv8 #midjourneystyleexplorer #stylefinder#aiart #aivideo #aiworkflow #weavy #freepik #higgsfield #promptengineering #aiimagegeneration #generativeai #texttoimage#midjourneytips---⏱️ Midjourney Fast Hour[00:00] Cold open, Halloween vibes, aging gracefully (or not)[02:32] Scream, Stranger Things, Blade nostalgia[06:19] Kids’ costumes, seasonal prompting (moody fall looks)[07:43] Midjourney Office Hours recap: V8 hype, maybe skipping 7.1[09:14] Draft Mode real talk; permutations (exp, chaos) habits[11:38] “Try style” quirks and SRF stacking behavior[14:04] Deep dive: Style Explorer (search by tokens, textures, cameras)[18:00] Token combos for discovery [20:46] Treating styles as presets; niche searches [25:04] “This is my new obsession” → why the search now lands[28:15] Style Creator talk and the coming no-words UI paradigm[31:22] New UI learning curve; what should get simplified or cut[32:10] “Pan/Zoom” redundancy; grid-UI vs chat-UI debate[35:22] Option overload vs micro-tools; how people really adopt features[36:28] Editing & creative features pipeline, edit models, multi-image refs[41:31] Weekly release cadence returning; “sailboat”/secret-projects notes[43:19] Market share, comms, and why MJ must show up on more channels[46:46] Freepik: models, workflows, collections, brand-swap use cases[52:26] From icon packs to aggregator; Canva/Krea comparisons[58:00] Genie note; Higgsfield’s “rage-bait” marketing, Popcorn storyboard[1:00:04] Camera-move snippets as prompt clauses (easy wins)[1:05:05] Higgsfield Chrome extension → “Recreate” → steal the prompt skeleton[1:10:59] Turn that skeleton into a reusable prompt template[1:12:44] Weavy fan-out: test same prompt across 6–8 generators fast[1:15:45] Comparing results; where each model shines[1:17:28] The nugget for the real ones + sign-off and Halloween tease

Rory and Drew try to keep up with AI like two dads jogging after a runaway stroller. They dig into Midjourney v8 rumors, the new Style Finder vs. Style Creator, and why personalization has everyone stuck in a pink-blue haze. They compare Sora 2’s shock-tightened IP rules to Veo 3.1’s practical upgrades, then sprint through Runway’s new “apps,” Reve’s under-the-radar glow-up, and a wild photo tool (Phota) that restyles real shots without wrecking the moment. It’s fun, a little chaotic, and weirdly useful.---⏱️ Midjourney Fast Hour00:00 – Cold open, what’s on deck this week02:50 – Midjourney focus: v8 push, V7.1 “flatline” expectations03:37 – Office Hours notes: V7 data “trash” comment, inconsistency feels06:39 – Midjourney’s lane vs. Nano-style natural language edits, hue/personalization fixes08:39 – Release vibes: David’s chipper mood, holiday-timing speculation09:29 – V8 → next video model; Style Finder vs. Style Creator; Style Explorer today13:33 – User profiles: do we actually want a social layer?16:21 – The unseen archive: making value from the 99.99% you never post20:10 – “Friends not followers” and smarter discovery without another social grind22:17 – Community events, MJ TV walls, style rankings, merch tease23:14 – Stickers, swag, hoodie season, and not becoming the mailman26:58 – Sora 2 afterglow: IP clamps, virality headaches, and death-threat absurdity31:59 – Rant: the skill shift from “right answers” to “right questions”33:57 – Veo 3.1: longer clips, start/end frames, sound tweaks, quarterly cadence39:11 – Why Sora is quietly best at humor and timing40:04 – The future of social: less followers, more friends, fewer ads42:39 – Runway “apps”: micro-tools that make editing obvious44:05 – Reve’s relaunch: edit-any-image, reverse search, excellent skin/texture46:34 – Photo Labs: restyling real photos without losing the moment50:44 – Wrap: building real workflows across tools, not just vibes52:31 – “Poke it with a stick”: like, sub, share, we’ll keep it under an hour---#midjourney #midjourneyv8 #midjourneytutorial #midjourneyai#midjourneyart #midjourneyupdate #midjourneystyle #midjourneycommunity #aiart #aigeneration #aiarttutorial #generativeai#aiimagegeneration #digitalart #creativeai #Style Finder #Style Creator #midjourneypersonalization #sora2 #veo3 #Runwayapps #reveai

Midjourney Fast Hours — Episode 51: “Sora 2, Veo 3 & The AI Video Gold Rush”Drew and Rory crawl out of their creative caves after a month-long “break” (read: total burnout) and immediately get smacked in the face by Sora 2, Veo 3, and Midjourney Style Explorer updates that make everything they said last episode obsolete.They break down what’s actually working in Sora 2 (full edits, audio, dialogue, even IP?), why Veo 3 can’t seem to go fast anymore, and how keyframes are quietly becoming the holy grail of AI video.Expect rants about IP chaos, Mr. Rogers cameos, and why OpenAI’s guerilla launch strategy might be the smartest marketing move of 2025.It’s equal parts therapy session, tech panic, and creative caffeine rush — exactly how they like it.Keywords: Sora 2 update, Google Veo 3 review, Midjourney V8, AI video generation tools, Luma AI, keyframes, AI video editing, AI marketing trends 2025, generative video, Style Explorer Midjourney---⏱️ Midjourney Fast Hour00:00 – Intro + return from creative hibernation00:42 – Sora 2 drops: “the floodgates just opened”01:27 – Sora 2’s new tricks: editing, sound, dialogue, and IP02:17 – Veo 3 vs Sora 2 vs Ray 303:20 – Rory’s South Park AI episode + the “bar-only” friend05:00 – Why dedicated AI-only spaces actually matter05:48 – Remix culture, Mr. Rogers AI, and the rise of comedic timing07:00 – The “Remix” button, mass adoption, and kids using Sora08:43 – The IP gray area: Minecraft meets Mr. Rogers09:43 – Cameos, access codes, and mobile vs desktop creation12:25 – Sequential storytelling: AI understands chronology now13:29 – Toyota ads, guerrilla launches, and OpenAI’s flood strategy15:00 – IP risk vs reward — how far can brands push it18:00 – AI performance comparisons23:00 – Fight scenes, motion control, and why keyframes matter27:50 – Workflow troubleshooting and micro-decision fatigue34:50 – Too many tools? Runway, Aleph, and the Weavy advantage35:45 – Shout-out to Weavy + tool consolidation predictions36:00 – Higgsfield pivots, Pika memes, and the marketing gap37:00 – Visual Electric’s acquisition and the coming consolidation wave38:20 – Midjourney updates: Style Explorer, Smart Search, and new unlocks40:30 – Playing with EXP mode + hidden color/style refinements42:30 – Style Finder, Style Creator, and mood-board personalization43:57 – Style ranking feature + --r 40 nostalgia meltdown46:00 – Midjourney V8 speculation & dataset rumors50:30 – Google’s product chaos: Gemini, Nano Banana, Flow, and Veo 353:00 – Why Google can fail (and still win)55:10 – ChatGPT’s image text features & the next AI video wave59:30 – The Weavy renaissance and workflow automation discussion1:02:00 – New creative problems worth solving1:06:00 – Why “easy” AI creation still stings for creatives1:08:30 – Closing banter + “hit the button” outro

The Midjourney Fast Hours crew hits episode 50…and immediately forgets to throw a party. Instead, Drew and Rory stumble into a killer trick inside the brand-new Style Explorer (yes, that hidden Smart Search → Styles move), while guest Allar Haltsonen cheerfully roasts their “we’ll plan it later” energy and shows how RAW can completely flip a style’s look. They blitz through v7.1 notes, v8 teasers, and real-world Midjourney Video settings (SD vs HD, Loop vs Motion) before going full Nano Banana: Freepik in-app inpainting, aspect-ratio hiccups, and a slick Photoshop plug-in workflow. If you care about consistent aesthetics, faster iteration, and finding SREF styles without burning credits, this one’s pure potassium.Search hooks & keywords: Midjourney Style Explorer, SREF / SREF style codes, Smart Search trick, RAW parameter, v7.1, v8, Midjourney Video settings, Loop vs Motion, SD vs HD, OREF, Nano Banana, Freepik inpainting, Photoshop plug-in, fashion swaps, cinematic angles, moodboards, style weight, stylize.---⏱️ Midjourney Fast Hour00:00 — Episode 50?! housekeeping + cold open00:06 — The “like & subscribe” bit (tell your mom, dog, everyone)01:19 — What’s new + Allar intro; Office Hours headlines01:49 — Style Explorer lands (why it matters for credits)02:30 — How it works: SRF codes, Explore tab, filters (Top/Hot/Day)05:07 — The pain of saving/organizing favorite SRFs06:07 — “Did they rotate styles?” + early content observations07:13 — Preview layout (character / environment / object)08:11 — Surprise: RAW massively changes some styles10:38 — The curly-brace RAW syntax gotcha during live tests14:36 — Smart Search → Styles hack (the hidden gem)18:34 — Image as SREF, weighting, and moodboard workflows23:40 — Office Hours: v7.1, OREF improvements, draft mode, v8 path25:48 — v8 is the big model rev; video waits until v8 ships26:49 — Midjourney Video: manual vs auto; motion vs loop30:23 — SD vs HD trade-offs (costs, quality)33:04 — When to upscale before animating (text handling quirks)35:29 — Profiles, friend rooms, global rooms, prompt battles37:26 — Discord nostalgia: forgetting “/imagine” (oops)38:22 — Nano Banana deep dive: why it’s workflow-changing40:40 — Where to run it: Freepik, KREA, Google AI Studio, Higgsfield41:01 — Aspect-ratio hiccups & hacks in Freepik44:15 — In-app inpainting & reference characters in Freepik45:00 — Nano Banana Photoshop plug-in (enable & flow)48:25 — Pro tip: consistency over heavy retouching50:54 — World-building workflows: zooms, angles, new actions53:20 — Consistency challenges: missing doors, mismatched details56:00 — Adding characters & branded clothing to complex scenes58:20 — Character sheets + compositing tricks for consistency01:00:09 — Compositing disruption: Photoshop harmonize & Nano01:02:12 — Time-lapse edits (dust, rust, lighting changes)01:04:39 — True world-building: multiple lives & story arcs01:06:28 — Keep/change prompt trick for Nano Banana01:07:09 — Pushing realism: Nano Banana vs raw Midjourney01:08:42 — New media: character-as-influencer storytelling01:10:20 — Rosebud & branching narrative experiments01:11:46 — Simulation talk: where storytelling is heading01:12:45 — Wrap-up

Rory and Drew invite creative polymath Marco Isle to do what this show does best: break Midjourney in interesting ways. It’s a token binge from shadow play, moonlight, GOBO shadows, datamosh, pixel smear, prismatic rainbow light streaks, and androgynous beauty plus where --exp actually makes images better (and where it ruins them). They also crack open token bashing (smashing words to birth fresh visuals), show why aspect ratio is half the art, and steal moodboard fuel from Cosmos.so.Then it gets dangerous. Nano Banana enters the chat, turning one still into dozens of consistent shots with plain-English tweaks. They compare video stacks and frames workflows (Veo-3, Kling, keyframes), talk Weavy automation, and use a real “Book of Jonah” case study (42 scenes, ~5k images) to show how fast this all moves (and where it still breaks). It’s Midjourney’s magic, but with receipts.Keywords: Midjourney tokens, token bashing, EXP settings, aspect ratio, mood boards, Cosmos.so, Nano Banana, Weavy, frames, keyframes, Veo-3, Kling, AI image generation, Midjourney video, consistency, creative workflow.---⏱️ Midjourney Fast Hour00:00 — Cold open + guest intro (Marco Isle)00:35 — Marco’s background: design → UX/UI → fashion04:48 — Aesthetics vs. mechanics; the cooking/technique mindset10:50 — “Rome Reimagined” + early Frames testing15:59 — Token bashing & Marco’s custom GPT flow20:59 — Favorite tokens: shadowplay & moonlight21:32 — New token: gobo shadows (why it works)22:19 — Glitch looks: pixel smear & datamosh23:34 — Prismatic rainbow light streaks (stacking ideas)23:54 — Androgynous beauty as a control aesthetic25:22 — --exp sweet-spots (3, 7, 10, 13)27:17 — “Liturgical drift parade” prompt set30:24 — Why Aspect Ratio is everything34:12 — Idea sources: mood boards + Cosmos.so38:54 — Nano Banana enters the chat (workflow + why it’s different)42:15 — Case study: Book of Jonah (42 scenes, ~5k images)43:03 — Video models: Veo-3 notes + start/end frame43:33 — Weavy & automation; setting guardrails50:00 — NanoBanana pros/cons; real-world limitations52:51 — Frames: Kling vs others; aspect-ratio flips55:11 — Aspect-ratio workaround (whitespace expand)57:47 — Keyframes consistency test (the car roll)---LINKS:Nano Banana—Image Gen Documentation: https://ai.google.dev/gemini-api/docs/image-generation#prompt-guideMarco Isle on X: https://x.com/ai_artworkgenMarco Isle on Gumroad: https://markisle.gumroad.comDrew's 1% Midjourney Style Guide: https://dcbruck.gumroad.com/l/Midjourney-Course/ib3nsqs

MJ:FH Ep. 48—Midjourney just unlocked HD video for everyone, added new batch size controls, and teased more of Style Explorer, V7.1, and V8. Here’s everything you need to know.Two bleary-eyed nerds test Midjourney’s newest toys so you don’t torch your credits. In this run-and-gun lab, Drew Brucker and Rory Flynn cover the video update (batch size 1–2, HD now available), why Moodboards finally lives in the sidebar, and what V7.1 is poking at while V8 hogs the spotlight.They preview Style Explorer, debate O-Ref's re-emergence, and trade practical tactics for coherent, extendable shots without wasting fast hours. Expect detours into style codes, tokens (hello, “Homesteader”), and EXP vs Stylize in real workflows.Translation: a friendly chaos sandwich with updates, experiments, and a little self-roasting, while laying out clear takeaways you can steal today.---⏱️ Midjourney Fast Hour00:00 - Cold Opener08:35 - Midjourney Update Rundown09:04 - Video Batch Sizes 1–2 + HD Mode09:49 - Moodboards Sidebar Update11:27 - V7.1 Notes + O-Ref Talk12:14 - Early V8 Teasers18:53 - Style Explorer Preview20:16 - tyle Explorer Wishlist + Trends27:21 - Midjourney TV 29:38 - Token Talk: “Homesteader”32:14 - EXP Parameter Live Test33:45 - EXP vs Stylize Workflow34:30 - Stylize Confessions + Image Ranking38:39 - GPT-5 Hype vs Reality40:02 - Sora + Coherence Issues45:38 - HD Video in Practice46:37 - Missing “SD to HD” Button48:21 - Manual Prompting for Extensions54:44 - Text + UI in Midjourney Video56:40 - Video Troubleshooting Lab Idea57:33 - Fixing Video Coherence58:57 - Outro + Subscribe---

Rory’s apartment is in chaos, Drew’s talking about broken toes again, and somehow they end up deep-diving Midjourney TV like it’s cable circa 1999. In this episode, the guys go full nerd on Midjourney’s video loops, end frames, and personalized Explore Pages—plus fresh Office Hour gems on Style Explorer, V8 hints, and even video audio layers that could flip workflows on their heads. If you’ve ever wanted to know how to chain video keyframes without breaking your sanity (or your credits), this is your episode. Bonus: Vine nostalgia, Abercrombie comebacks, and more unsolicited fashion advice than anyone asked for.---⏱️ Midjourney Fast Hour00:00 – Drew opens with After Dark energy, Rory’s apartment woes01:00 – Midjourney TV first impressions (and why it’s weirdly addictive)04:30 – Personalized Explore Page walkthrough & “For You” feed09:40 – Style codes, crushed highlights, and Rory’s goat obsession14:30 – Style Explorer predictions & trending token ideas19:30 – Keyframe loops explained (and why composition matters)25:30 – Midjourney’s background erase + Photoshop pain flashbacks33:40 – Office Hour drops: mood board weighting & video turbo mode40:00 – Video pricing, audio layers, and sound’s “Rubicon moment”46:50 – Chaos & stylize parameters coming to video prompts50:30 – Secret projects, two-second video model & Vine comeback53:20 – Abercrombie flashbacks & heavyweight tee obsession57:20 – Heavyweights (the Ben Stiller kind) + Aleph’s video magic01:05:00 – Runway diagram prompting, ideogram shoutout, Mystic AI01:09:30 – Midjourney’s growth curve & why you need to dive in now01:12:00 – Like & subscribe pitch + one-year podcast anniversary---#Midjourney #MidjourneyTV #MidjourneyVideo #MidjourneyAI #AIart #AIGeneratedVideo #VideoLoops #EndFrame #aiworkflow #StyleExplorer #GenerativeAI #AIVideo #CreativeAI #AItools #AImarketing #AIcontent #VideoEditing #AImotion #Keyframes #AIcommunity

Rory accidentally finds himself on a nudist beach while Drew's making DIY sunscreen with AI. And if that wasn't crazy enough, this episode is a full live teardown of Midjourney video loops and end frame control—features built for creating cinematic AI video workflows. Drew and Rory show how to use loops, start/end frames, and extended keyframes to build seamless sequences, plus what to avoid so you don’t burn through credits.You’ll also learn:✓ Keyframe Extensions – chaining multiple shots for longer, smoother videos✓ JSON Prompting – precision timing and motion control (with live tests)✓ Runway Act Two – motion capture updates and creative comparisons✓ Midjourney Style Explorer & V8 Preview – what’s next for AI-driven video creationWhether you’re a creative director, designer, marketer, or experimenting with AI video workflows, you’ll get practical prompts, iteration techniques, and creative hacks to level up your Midjourney results.Watch now to see how these new features work, what to avoid, and how to produce cinematic AI videos faster.---MJ:FH Buddy (GPT)https://chatgpt.com/g/g-68755521d2348191a5ea8f6457412d51-mj-fh-buddy---⏱️ Midjourney Fast Hour00:00 – Intro & accidental nudist beach adventure02:50 – DIY sunscreen & unexpected AI life hacks07:00 – Midjourney video update overview (looping, 720p, start/end frames)10:20 – Upscalers, Magnific precision, and V8 development focus15:30 – Personalization codes & base model quality debate17:30 – Custom GPT for Midjourney knowledge recall21:10 – Mood boards, micro-styles, and avoiding “homogenous AI look”24:40 – Style Explorer, aesthetic preference survey, and upcoming features27:10 – Live first-frame/last-frame keyframe testing38:30 – Loop functionality and extended multi-keyframe workflows45:40 – Iterative prompting lessons and fixing motion quirks53:30 – JSON prompting explained and social-ready video hacks58:00 – Runway Act Two motion capture tests and impressions01:07:30 – Sloth race cars, Trump in Lord of the Rings & other AI absurdities01:09:40 – Key takeaways and what’s coming next

Rory and Drew are back and things get... weird. In this episode, they push Midjourney Video to its limits—trying to animate mushrooms, morph soda cans, and see what happens when you feed it your childhood art. Along the way, they break down the newest Office Hours updates, upcoming pro features, and the mystery of “unglued photography". Expect:Creative tests (some failed spectacularly)Deep video coherence takesSound design debatesAnd a suspicious amount of pasta sauceBonus tangents:Why product morphs make great ad assetsWhether Midjourney understands moodA casual existential spiral about sound designAnd the weirdest prompts of the week (of course)It’s experimental AI art meets late-night YouTube rabbit hole. Enter at your own risk.---⏱️ Midjourney Fast Hour00:00 – Cold Open & Midjourney Video Reactions03:00 – Animating Product Photos (Oranges, Candles, Chaos)05:30 – Selecting Images That Only Midjourney Can Handle07:00 – Auto Mode vs Manual Prompting in Midjourney Video10:00 – Emotion + Mood Prompting Still Works11:00 – Scuba Fins & Radial Blurs: Funny Animation Fails12:30 – Midjourney Office Hours Updates (Start/End Frames, Loops, Delays)13:30 – Native HD Pro Video (20x Cost!) Coming to Midjourney15:00 – Why 480p Might Be Better Than 1080p17:00 – Upscaling, Topaz Workflow, & Download Raw18:00 – Professional Video Features Coming Soon19:45 – Sound Feature Teasers: Ambient & SFX-Only for Now21:00 – Why Bad Sound Ruins Great Video24:00 – Layering Sound Like a Mindfulness Practice26:00 – Explore Page, Profiles & Social Signals in Midjourney30:00 – “Unglued Photography” Prompt Rabbit Hole36:00 – Chaos Tests, Permutations & Prompt Recall Trick41:00 – Live Video Testing (Rotation Patterns & Coherence)46:00 – Motion Details: Shoulders, Eyelids, and Rubbed Knees50:00 – Breaking Midjourney Video with Complex Shapes & Hole Faces52:00 – Animating Childhood Drawings (Real Example)56:00 – Product Morphs into Mushrooms: Asset Testing59:00 – Weevy Frame Extraction Demo1:02:00 – Morphing Abstracts to Realistic Motion1:04:00 – Kling vs Midjourney: Morph Comparison1:06:00 – Moodboard Updates, Looping, Profiles, API Launch1:10:00 – API Limitations & Why PLG Matters1:13:00 – Final Thoughts: What the Hell Is Coming Next?

Rory’s parents are laughing in the background. Drew just got a Midjourney tattoo that reads "/imagine". And somehow, Midjourney video dropped in the middle of all this.This week on Midjourney Fast Hours, the boys stumble into an accidental emergency episode because (surprise!), Midjourney just casually launched the most fun AI video tool yet. No press release. No tweetstorm. Just boom, it’s here. And it works. Like, stupidly well.They run live experiments, break down what’s working (and what’s weird), and unpack the shockingly seamless auto-prompt, motion settings, extend feature, 4-up grid, and how it plays with SREF. Spoiler: SREF just got way more powerful—and more confusing. Also, Drew finds a way to sneak himself into a talking head video, naturally.Think you’re burned out on AI? This might be the update that gets you feeling things again.---⏱️ Midjourney Fast Hour[00:00] Thursday night chaos & surprise video drop[03:40] Midjourney’s whisper video launch strategy[05:10] A wave of feature updates: SREF, video, pricing[06:15] Long-term vision: real-time world-building[07:00] First impressions of Midjourney video[08:30] Auto-prompt is criminally good[09:55] High motion vs low motion—how to choose[12:24] The magical 4-grid video preview[14:00] Interface brilliance: simplicity done right[15:20] Observations on motion templates & quirks[17:00] Animation consistency & style fidelity[18:30] Old stills, new life—archive resurrection[20:00] Using SREFs to build entire worlds[22:50] Where the current video model falls short[24:20] Enter Topaz Astra—perfect timing for upscaling[26:00] A personal story on AI, portraits & impact[28:40] Upscaler comparisons: Magnific vs Bloom[30:00] Visual bugs: wheels, backwards cars & physics[32:00] Why hands magically fix themselves in video[34:00] Face consistency & surprising details[36:45] Sneaking Drew & Rory into an animated video[37:30] New Explore page for video (and why it rules)[38:50] The Extend feature is shockingly seamless[40:15] Camera direction tips for better results[42:20] Prompt control vs camera behavior when extending[44:10] Wild new video prompts spotted on Explore[47:00] Midjourney’s edge: vibrant color retention[51:00] SREF update — what broke, what’s better[54:15] Favorite tokens: dribbble.com, Nike ads, stoicism[57:40] Using songs, moods, and weirdcore to test SREF[59:15] How --exp interacts with --sref (and when to dial it down)[01:03:00] SV6 vs SV4 — why it matters now[01:08:00] Building smart prompt batches for testing[01:10:20] Describe tool to reverse-engineer SREF aesthetics[01:17:00] Style reference vs subject leakage test[01:23:45] Personalization wish list: can ranking images help?