EP 053 · 79 MIN RIGHT-CLICK STEALS THE EXACT AI PROMPT
Cracking Midjourney’s Style Explorer + Freepik’s Rise + Higgsfield Prompt Hack
The short version
Episode 53 treats Midjourney's Style Explorer as a token-based search engine, tours Freepik's shift into a full creative 'aggregator' platform, and demos a Chrome-extension trick that reveals the exact prompt behind any image recreated in Higgsfield. Rory and Drew turn that extracted prompt into a reusable JSON-style template with ChatGPT, then fan it out across Weavy to Reve, Mystic, Flux 1.1, Ideogram and more to compare results.
Key takeaways
- 01
Search Midjourney's Style Explorer by specific token instead of broad category: words like 'grainy deep texture' or 'blacklight interface' surface styles browsing alone won't find.
- 02
Higgsfield's Chrome extension can Recreate almost any image you right-click on the web, then shows the exact prompt it used, ready to copy elsewhere.
- 03
Turn an extracted prompt into a reusable JSON-style template (lens, subject, wardrobe, scene, props) with ChatGPT, then swap variables instead of writing from scratch each time.
- 04
Test one prompt template across many image models at once: Rory and Drew fanned a single Higgsfield-sourced prompt out to Reve, Mystic, Flux 1.1 and Ideogram inside Weavy in minutes.
- 05
Freepik now bundles Nano Banana, Mystic and Runway plus templated mockup 'collections,' but Drew and Rory both call its navigation clunky and hard to market.
- 06
Midjourney may skip V7.1 entirely and jump straight to V8 unless a single feature is substantial enough to justify shipping on its own, per Office Hours.
- 07
Minimax quietly capped Rory's paid yearly 'unlimited' plan after a pricing change, moving him to a limited tier without warning despite paying upfront.
Receipts · said on the record
“you can get, you can get like pretty specific, almost like you're researching for tokens, which I was like sick. I really like this.”
“Like I don't want to chat with it. Some people might, I don't. I like the options of four images and like push some buttons, not like do this. Okay, now do this. Then like scrolling back through all that stuff.”
“I think Higgsfield, the whole marketing plan is just like, it's just rage bait. Like, I think that's the entire marketing strategy is just rage bait.”
“To me, it's not about getting the image. It's about just like, cause Higgsfield will show you the exact prompt it used to create it. So I just go and use like that prompt.”
“But the impact and significance of this, and the application of it, how often you're going to use this is insane. So if you've not done this by now, you should.”
“I bought the yearly unlimited last year because it was such a good deal. It was like three hundred dollars for the year for unlimited … But then when they dropped to two, it was like, oh sorry, you're grandfathered out of that.”
Chapters
- 0:00:00 Cold open, Halloween vibes, aging gracefully (or not)
- 0:02:32 Scream, Stranger Things, Blade nostalgia
- 0:06:19 Kids’ costumes, seasonal prompting (moody fall looks)
- 0:07:43 Midjourney Office Hours recap: V8 hype, maybe skipping 7.1
- 0:09:14 Draft Mode real talk; permutations (exp, chaos) habits
- 0:11:38 “Try style” quirks and SRF stacking behavior
- 0:14:04 Deep dive: Style Explorer (search by tokens, textures, cameras)
- 0:18:00 Token combos for discovery
- 0:20:46 Treating styles as presets; niche searches
- 0:25:04 “This is my new obsession” → why the search now lands
- 0:28:15 Style Creator talk and the coming no-words UI paradigm
- 0:31:22 New UI learning curve; what should get simplified or cut
- 0:32:10 “Pan/Zoom” redundancy; grid-UI vs chat-UI debate
- 0:35:22 Option overload vs micro-tools; how people really adopt features
- 0:36:28 Editing & creative features pipeline, edit models, multi-image refs
- 0:41:31 Weekly release cadence returning; “sailboat”/secret-projects notes
- 0:43:19 Market share, comms, and why MJ must show up on more channels
- 0:46:46 Freepik: models, workflows, collections, brand-swap use cases
- 0:52:26 From icon packs to aggregator; Canva/Krea comparisons
- 0:58:00 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
Questions this episode answers
How do you search Midjourney's Style Explorer effectively?
Rory recommends typing specific tokens rather than broad categories: words like 'precision photography,' 'grainy deep texture' or 'blacklight interface' surface styles you wouldn't find just browsing the Top or Hot tabs.
What is the Higgsfield Chrome extension prompt-stealing trick?
Right-clicking an image on the web and choosing Recreate runs it through Higgsfield's Soul model and shows the exact prompt used, which Rory then feeds to ChatGPT to turn into a reusable prompt template.
Is Freepik worth using as an all-in-one AI tool?
Drew and Rory say Freepik now bundles most major models (Nano Banana, Mystic, Runway) plus templated mockup 'collections,' but both call its navigation and structure clunky and hard to market.
Will Midjourney release V7.1 before V8?
Per Office Hours notes discussed on the episode, Midjourney may skip V7.1 entirely and go straight to V8 unless a feature is substantial enough to ship on its own.
What happened to Minimax's unlimited plan?
Rory paid about $300 for a yearly 'unlimited' Minimax plan, but says a later pricing change quietly moved him to a limited tier without notice.
Show notes
Fast Hours Podcast Ep. 53—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
