Fast Hours

What Can OpenAI’s Astra and GPT Image 2.5 Actually Do?

So, what can OpenAI’s Astra and GPT Image 2.5 actually do? Drew Brucker and Rory Flynn put OpenAI’s Astra and GPT Image 2.5 models through a golf course build, a vintage typewriter animation, and a round of image edits. Rory’s golf course experiment burns 70% of his weekly allowance. Drew spends three hours getting a typewriter to type. Their gift for turning a quick test into a side project remains undefeated. The pro-AI half of the show. The other half: a viral AI resignation that looks planned to the minute, Anthropic's 154-page report on how people misused Claude, and GPT Image 2.5 quietly fixing the reasons everyone kept running back to Nano Banana. This episode covers OpenAI Astra with computer use, two ChatGPT chats collaborating inside one project, Three.js and Blender renders, a fantasy football analytics hub, and Astra running Midjourney with mood boards and style references. GPT Image 2.5 multi-edit comments, sketch input, custom aspect ratios, and template creator. Anthropic's threat report, Moonshot and Kimi distillation, and the viral AI researcher resignation. --- ⏱️ Fast Hour 00:00 What’s on Fast Hours this week? 06:35 Why do traumatic moments burn into memory 07:42 What was different before social media 13:48 This week: Astra, GPT Image 2.5, a viral resignation 15:04 Did an AI researcher really resign over ASI 18:40 How to tell what is true in AI news 20:42 Why quitting your AI job can't stop superintelligence 27:01 What do the cited reports allege about Kimi 28:33 What AI misuse examples do the hosts discuss? 34:07 How did Astra build a golf course prototype? 35:35 How did research improve Astra’s first attempt? 36:33 What happened when two AI chats collaborated? 39:29 Why did Rory stop the drainage research? 40:02 How did Drew approach his Blender experiment? 40:52 How did Astra recreate Drew’s typewriter? 43:49 How long does AI-assisted 3D work take? 44:43 How did Drew build a ChatGPT dashboard? 48:32 What happened when Astra explored Midjourney? 53:56 How did mood boards shape Astra’s prompts? 58:49 What improved in GPT Image 2.5? 01:00:24 How do GPT Image 2.5 edit comments work? 01:01:47 How do you request multiple image variations? 01:03:30 How well did GPT Image 2.5 resize ads? 01:07:11 How reusable templates in GPT Image 2.5 can help brands 01:08:37 What’s coming next for Fast Hours?

How We Use AI to Run Our Businesses With Skills, Agents & MCPs

To run a solo business on AI, build a system of small skills and agents that handle the admin, comms, and ops so your time goes to creating. --- Two founders who swore AI would give them their time back open the hood on what they actually run. Drew walks through 37 hand-built skills and a 21-layer system for writing in his own voice. Rory runs his whole business out of Notion and Claude, down to finding an online fax machine for New York State. Neither of them can remember what half their own skills do. That's kind of the point. This episode covers building an AI operating system for a one-person business. Topics include Claude skills and agents, a voice system for writing, email and call ingestion, Notion as a CRM, red-teaming contracts and MSAs, predicting LinkedIn reach, Nano Banana prompt engineering, and handling taxes, invoices, and vendor forms. Fable and Astra model releases open the show.

A 24 Year Old AI Creative Director Gives Away Her Playbook (feat. Jamey Gannon)

An AI creative director combines design fundamentals, AI fluency, tool selection, and repeatable workflows to produce better creative work. The boys over at Fast Hour invites a 24-year-old AI creative director to give away her playbook and somehow gets reminded that buying more AI subscriptions does not count as mastery. Jamey Gannon explains why AI is a skill, what top operators do differently, how Midjourney mood boards become brand systems, and why sometimes the smartest AI move is opening Photoshop. Jamey Gannon explains how self-taught design, social media, freelancing, and AI fluency shaped her work as an AI creative director. Jamey Gannon demonstrates Midjourney mood boards, SREFs, Midjourney V8.2 Edit, Krea K2, Claude, Figma, Photoshop, Flora, Nano Banana, and the CXO brand system, including when to build custom tools instead of forcing an existing workflow. --- ⏱️ Fast Hour 00:00 Who is Jamey Gannon? 06:43 How Jamey taught herself design at 15 12:23 Why Gen Z chases money over job titles 15:35 What first freelance clients look like at 17 18:43 Why social media is a freelance prerequisite 22:16 Freelance math: 20 clients vs one salary 24:13 How her sister makes $5K–$10K/month with AI 27:08 What is an AI creative director? 28:58 What the AI Creative Director course teaches 33:05 Is Krea catching Midjourney? 35:53 The "easy, fast, cheap" AI lie 38:43 Three moments that hooked Jamey on AI 42:23 How to build brand mood boards 46:00 How one SREF cracked the brand style 46:27 Midjourney + Figma: the pixel shader pipeline 49:06 When you should not use AI 51:53 Two ways to use Midjourney mood boards 56:44 What top AI creatives do differently 59:44 Build the tool when the workflow doesn't exist 1:11:28 Midjourney V8.2 Edit: first live tests 1:15:00 What works and what drifts in Midjourney Edit 1:20:06 Midjourney Edit vs Nano Banana: identity lock 1:21:32 Can Midjourney edit text and fonts now? 1:25:23 Can Midjourney's edit model preserve logos and apparel graphics? 1:31:05 Is Midjourney inpainting or regenerating? 1:34:33 The verdict: using Nano Banana less 1:37:34 Where Nano Banana still fits

AI Workflows Brands Actually Pay Five Figures For

Brands pay five figures for AI workflows that turn repetitive creative work into reusable systems teams can run at scale.Drew Brucker and Rory Flynn speedrun their way into a useful business model while trying to explain node-based AI without melting anyone’s brain. The opportunity itself is practical. Find expensive, repetitive creative bottlenecks, turn them into reusable workflows, and make the complicated machinery simple enough that an entire team can actually use it.The boys break down Figma Weave, node-based AI workflows, system prompts, batch processing, arrays, Claude, ChatGPT, Gemini, Flux, Nano Banana, Gen Effect, and MCP. SharkNinja and BarkBox examples show how AI workflows support localization, product visualization, asset re-versioning, creative production, team handoff, and scalable content generation.The bigger idea here is that the value comes from encoding the process, creative logic, and standards into a system that can be reused across hundreds of assets without starting from zero.#AIWorkflows #CreativeAutomation #GenerativeAI #FigmaWeave #aiforbusiness ---⏱️ Fast Hour00:00 Cold opener07:22 Why a full Figma Weave episode09:53 How node workflows went mainstream in a year14:10 Why use a node-based AI tool at all?19:02 Inside the Figma Weave AI toolbox20:53 How to sell AI workflows to businesses23:24 Why brands pay five figures for AI workflows24:33 How SharkNinja localizes across 35 markets30:07 Why recurring tasks belong in workflows31:34 Live build: your first AI workflow39:09 What the Gen Effect node can do44:00 How to turn an image into a 3D asset48:46 Scale one fashion image into reusable assets55:18 How to build a batch-processing engine1:03:24 Prompt vs system prompt: what's the difference?1:05:38 Turn a node graph into a reusable tool1:12:17 Engineering an automated listicle video1:14:51 One-shot video vs modular AI production1:24:29 How BarkBox fixed one production bottleneck1:35:20 Where AI workflows create business ROI1:38:20 Why workflows survive every new AI model1:39:29 Paste your workflow into Claude to debug it1:42:57 Use AI workflows as callable functions1:44:28 Publish your workflows into Claude MCP1:46:09 Resources and wrap-up---FIGMA WEAVE 15% OFF: Use code FASTHOURS15 at checkout- 15% off the first purchase of a Figma Weave Starter, Pro, or Team subscription- One-time use per person- Applies to the first month (for monthly plans) OR first year (for annual plans)OUR FREE FIGMA WEAVE WORKFLOWS: Drew's Apparel Photoshoot: https://app.weavy.ai/flow/JV8vBtbkOl3vNeiJjAYwxN Drew's Product Social Images: https://app.weavy.ai/flow/la8iMD20eGX4eGF91qunVu Rory's Listicle: https://app.weavy.ai/flow/SpLj0jsU8hThMmHWtfmT37 Rory's SD2.5 Prompting: https://app.weavy.ai/flow/MdYt6UJi6ch0MkgxTaCe6r Rory's GenEffects Collage: https://app.weavy.ai/flow/sX4dJgsrp9DIrOz5f9ojX1 Rory's Batch Generator: https://app.weavy.ai/flow/f9OljOQLkPbJ9Q04iN8Uou Rory's El Camino Concept: https://app.weavy.ai/flow/BPfVXywHhoymEi3CFxOO3Q

He Built an 8 Figure AI Business in One Year (feat. Rourke Sefton-Minns)

Rourke Sefton-Minns scaled his AI creator business from zero to eight figures in one year by turning audience, education, and creative AI into a business system.Drew and Rory invited Rourke Sefton-Minns on to discuss AI and somehow ended up reverse-engineering a business built on sleep streaming, 420 straight days of posting, multiple failed creator experiments, hitting zero in the bank, and an apparently unhealthy refusal to quit. Rourke breaks down how Gen HQ grew, why brand partnerships now drive hundreds of thousands in monthly revenue, why learning AI tools is often the least important part of getting paid, and why the best move for aspiring AI creatives may be finding the client before figuring out every last detail.Rourke Sefton-Minns explains Gen HQ, AI creator businesses, brand partnerships, LinkedIn client acquisition, spec work, creative partner programs, Meta advertising, Adobe Photoshop Generative Fill, CapCut, Google Gemini, node-based workflows, narrative-loop content, creator burnout, AI careers, and generative AI-powered fandom. He also shares a practical three-month playbook for landing paid AI creative work and his mission to create 100,000 jobs for creatives through AI.---⏱️ Fast Hour00:00 Rourke Sefton-Minns, Gen HQ and 100K jobs02:55 Five social pages before the one that worked05:03 The sleep-streaming business that changed everything09:03 Making $10K a month at 21, then burning out13:04 Betting everything on a six-month ski channel17:11 The persistence lesson behind hitting zero20:50 420 days of posting before the AI pivot28:40 Why Gen Z sees generative AI as the enemy33:01 Why great AI content starts with communication35:10 Inside his vibe-coded content idea system39:19 How long a viral AI video takes to make43:20 Why AI creators burn out46:14 Outsourcing creativity made burnout worse47:27 Why changing formats brought the fun back50:25 How narrative-loop videos create retention52:44 How his 8-figure AI business makes money56:10 Why $40K a month in Meta ads is not enough57:12 The business skills AI creatives overlook01:00:51 The 100,000-jobs North Star01:03:29 How to land your first paying AI client01:07:51 What major AI brands actually want01:12:30 Why boring products can win spec-work clients01:14:09 The four-post strategy for winning brands01:17:47 AI fan content as a new growth engine

How to Build an AI Universe That Compounds (feat. BLVCKL!GHT)

Build an AI universe by compounding recognizable characters, consistent worlds, recurring stories, and creative assets instead of starting from zero. ⁨ BLVCKL!GHT has spent thousands of hours doing the thing most AI creators accidentally avoid: sticking with one weird idea long enough for it to become an actual universe. Route 47 now spans 28 interconnected shows and characters, four seasons, recurring locations, expanding lore, and even a game in development. characters → worlds → stories → audience → distribution → monetization Drew and Rory dig into: + how creative consistency becomes leverage + why cult audiences can beat virality + and why every finished asset can make the next one easier to create. BLVCKL!GHT breaks down AI world-building, Route 47, original AI IP, character development, consistent AI art styles, audience compounding, and FAST TV distribution. Krea, Magnific, MiniMax H3, Seedance 2.5, Flux 3, Runway, RunComfy, Comfy Cloud, Higgsfield, and Luma Dream Machine frame the AI image and video workflow discussion. AI agents, creator economics, model costs, synthetic media, and creative ownership shape the broader conversation. --- ⏱️ Fast Hour 00:00 Who is Blvckl!ght? 04:15 Why did Blvckl!ght change his mind on AI? 09:06 Why does Gen Z hate AI but love his work? 12:15 What shaped Blvckl!ght's visual style? 16:19 What is Route 47? 19:04 How do you build an AI universe? 22:31 How do you stay creatively consistent? 24:35 Which AI tools does Blvckl!ght use? 26:42 Can AI agents make creatives slower? 29:14 Why can a cult audience beat virality? 30:15 How can AI creators monetize on FAST TV? 32:44 How does AI content reach mainstream media? 34:34 How do AI film projects get financed? 38:14 What is “Hi-Fi Slop” and why does it fail? 40:00 How do shorts become a real series? 46:52 Why can obvious AI feel more authentic? 47:57 What is AI's real creative opportunity? 50:14 MiniMax H3 vs Seedance 2.5 53:38 Local AI video vs cloud generation 54:39 How fast can one AI creator produce? 55:55 What is Flux 3? 56:57 How do you control AI generation costs? 59:06 How do unlimited AI generations work? 01:00:29 Brand equity vs capability in AI tools 01:03:26 Why do creators stay loyal to AI tools? 01:10:13 Where should AI creators draw the line? 01:18:26 Should AI make personal decisions? 01:27:01 Where should you start with Route 47? 01:28:45 How can AI check story consistency?

How to Build AI Workflows That Never Start From Zero

A good AI workflow remembers what worked last time, so you don’t have to rebuild the same process from scratch.Drew Brucker and Rory Flynn attempt to explain how advanced AI workflows actually work, then accidentally expose the mildly concerning machinery behind their own. The useful version of AI goes far beyond isolated prompts. It remembers prior decisions, pulls from real conversations, reuses approved skills, evaluates its own output, and saves the human from rebuilding the same process every Tuesday like a highly caffeinated goldfish.The episode breaks down context files, AI agents, evaluation loops, prompt amplifiers, reusable skills, call transcripts, sales data, and personal knowledge systems. Drew and Rory also examine Seedance 2.5, Midjourney V8.2, emerging AI-assisted 3D workflows, synthetic video detection from NVIDIA, LinkedIn’s AI slop button, and the growing gap between generating faster and building systems that improve with use.---⏱️ Fast Hour00:00 What is next for Fast Hours?05:39 Why criticize AI while using it?08:56 How can AI recover old creative work?10:46 Why did 90s sports design feel better?19:07 What is LinkedIn's AI slop button?22:37 Why did LinkedIn reward lower effort?29:10 How are creators gaming account reach?32:43 Why do large platforms ship so slowly?33:48 What changed in Seedance 2.5?39:57 What is new in Midjourney V8.2?43:48 How does texture improve AI prompting?49:25 Why is Midjourney regaining momentum?50:04 Why is AI entering its 3D moment?58:12 Can people still detect synthetic video?01:01:21 How does NVIDIA detect fake video?01:07:10 Why does speed devalue AI creative work?01:11:13 How do eval loops prevent AI slop?01:13:00 How can calls create original content?01:16:20 Why can't AI automate your opinion?01:21:54 What should AI content systems ingest?01:25:27 How can AI improve sales calls?01:29:41 Why should prompts stop starting at zero?01:31:08 How should AI skills be customized?01:33:29 When should AI workflows be deleted?01:35:12 How do you build an AI skill vault?01:38:23 What is Fast Hours' next milestone?

How to Make AI Images That Don’t Scream “I Used AI” (feat. Finn McKenty)

AI images stop looking generic when creators steer models with real expertise, original references, hand-built assets, and selective craft. Finn McKenty joins Drew Brucker and Rory Flynn to explain why the fastest route to better AI work may involve drawing by hand, reading the manual, and making fewer things. The three alleged efficiency experts also wander into AI burnout, fake UGC, Higgsfield trust problems, Midjourney’s long game, and the deeply inconvenient possibility that one great image may beat the 1,000 they can generate before lunch. Topics and tools covered:Midjourney, Weavy, ComfyUI, Claude, Gemini 2.5, GPT Image, Nano Banana, Flux, Krea, Figma, Adobe Photoshop, and Higgsfield anchor the practical discussion. Sketch references, image references, style references, out-of-distribution inputs, material-specific prompting, systems thinking, AI adoption, fake UGC, creator trust, and durable AI-assisted SEO define the core concepts. --- ⏱️ Fast Hour 00:00Who is Finn McKenty? 03:13 Why did Finn quit YouTube? 05:30 Do creators need a large audience? 12:05 Which existing skills create an AI edge? 14:26 Does expertise accelerate AI mastery? 16:27 Are creatives too attached to process? 18:17 Why do companies fail to adopt AI? 20:17 Why does advanced AI work cause burnout? 27:33 Where should creators invest brainpower? 29:31 How do creators steer probabilistic AI? 31:27 What made Midjourney click for Finn? 34:00 How did AI produce 10x SEO traffic? 37:44 Why reject polished AI perfection? 38:41 Why does handmade design feel better? 41:06 How should AI and manual craft combine? 46:24 Why does making more have zero value? 50:57 How does material knowledge improve prompts? 55:03 Why choose Weavy over ComfyUI? 55:44 How do sketches improve AI images? 58:33 How should creators divide work with AI? 01:02:12 What does out-of-distribution mean? 01:05:56 How do original references beat AI slop? 01:07:03 Why does fake AI UGC destroy trust? 01:11:31 What went wrong with Higgsfield? 01:22:33 Why did Midjourney acquire Co-Star? 01:24:09 Has Midjourney had the right vision? 01:27:30 Why are creators returning to Midjourney? 01:29:10 Why does bootstrapping protect creativity? 01:34:01 Why does AI creative work need fun again? 01:35:04 Does direct attribution kill creativity? #Midjourney #AICreativity #AIDesign #GenerativeAI #FastHours

How AI Is Making Human Creativity More Valuable

AI is making creative production faster while increasing the value of human craft, imperfection, and hands-on creative control.Drew and Rory start with Netflix’s 300 AI-assisted programs and somehow end up defending Blockbuster, boxy cars, greasy roommates, and the radical act of making creative work harder on purpose. Between the usual intellectual potholes, they uncover why invisible AI succeeds, why perfect outputs are becoming exhausting, and why human-made work may become the premium signal.Covered in this episode:Netflix generative AI workflows span concept development, pre-visualization, visual effects, post-production, and release. Suno, Udio, Strudel, Foley artistry, AI music licensing, Runway visual storytelling, Claude, ChatGPT, Figma shaders, Photoshop retouching, creative consistency, nostalgic design, imperfect aesthetics, and hybrid human-AI production define the broader creative shift.---⏱️ Fast Hour00:00 Why are guests returning to Fast Hours?03:45 Why does summer trigger nostalgia?10:49 How is Netflix using generative AI?20:39 Could Blockbuster have become Netflix?24:04 What AI tools has Netflix open-sourced?28:36 What did the Suno breach reveal?32:21 Should AI be used to make music?43:31 Breaking down Runway's lamp film—hy does it work?51:43 How many movie story arcs exist?53:32 Does AI increase the value of human craft?57:53 Why are creators rejecting AI perfection?01:06:16 Why is nostalgic design returning?01:17:09 Why do simple stories feel better?01:23:09 How do AI projects maintain consistency?01:25:43 Who should Fast Hours interview next?#GenerativeAI #AIFilmmaking #AIMusic #CreativeProcess #FastHours

She Cracked AI Advertising Before Brands Were Ready

In Episode 73, Salma Aboukarr joins the show. A creative director and founder, she explains how she moved from painstaking CGI workflows in Blender and 3Ds Max to AI-native campaigns for brands including Coca-Cola, Panasonic, and Google Labs. She breaks down her viral IKEA exploding-room video that helped brands see the commercial potential of generative AI video, the detailed JSON prompting method behind it, and the modern AI creative stack she uses across Claude, Midjourney, Nano Banana, Seedance, FAL.ai, Z-Image Turbo, Qwen, style LoRAs, and custom AI agents.The conversation goes deep on AI advertising, product fidelity, photorealistic skin, color correction, video upscaling, automated client workflows, and why high-end AI work still depends on original concepts, trained taste, and obsessive finishing. They debate whether AI can truly be original, why technical teams struggle to manufacture taste, how creators survive a feed flooded with AI content, and why the next creative moat may come from the experiences, references, and strange little details nobody else can copy.---⏱️ Fast Hour00:00 Meet Salma Aboukarr02:17 From CGI agency to AI-first studio04:44 Product fidelity before AI got good07:34 The duct-taped road to photorealism11:10 Art direction beyond basic prompting14:28 Salma’s current AI creative stack16:08 How she stress-tests every new model20:20 Why color correction still matters22:25 The IKEA video that changed everything27:13 Going viral and handling AI backlash30:38 Originality as the next creative moat33:05 Can AI actually be original?38:52 Inside an AI-native creative agency39:55 Z-Image Turbo and aesthetic base models43:06 From client brief to automated pipeline47:54 Style LoRAs for brand consistency49:11 Claude, MCP, FAL, and leaving ComfyUI51:07 The model that cut a day to 15 minutes55:13 Why AI content stopped feeling special01:00:57 The value trapped in AI archives01:02:06 Create for yourself or the audience?01:04:31 Can engineers manufacture taste?01:08:38 Finding inspiration outside the feed01:11:57 Jackie Chan and thumbnail fuel01:15:29 Final lessons from a creative trailblazer#AICreative #AIAdvertising #GenerativeAI #AIVideo #CreativeDirection #Midjourney #ClaudeAI #NanoBanana #SeedanceAI #AIWorkflow #AIAgency #AIContentCreation #BrandMarketing #CreativeTechnology #ProductPhotography #AIBranding #FutureOfAdvertising #FastHours

Taste Isn't the AI Moat You Think It Is

The boys are back with episode 72, where Rory Flynn and Drew Brucker attempt to discuss AI like serious adults. Yeah, that didn't work. They immediately detour into Figma Config, Waymo trust issues, Invisalign lisp watch, and the quiet horror of paying for AI models that may or may not be getting nerfed behind the curtain. This one gets into the big question creative teams keep circling: is taste still a moat in the AI era? Drew and Rory break down why “taste as a moat” is getting shakier, what types of taste are actually durable, and why timing, novelty, cultural awareness, editorial judgment, brand systems, and compounding context may matter more than ever. They also dig into Claude Fable, government access to stronger AI models, the widening gap between public and private model capability, Figma’s new AI workflows, Weavy integration, Adobe Firefly Foundry, Disney’s custom AI model deal, and Midjourney’s V8.2 preview, texture upgrades, editing roadmap, and secret search tricks. ---⏱️ Fast Hour00:00 The boys are back00:11 Rory recaps Figma Config03:13 Rory tries Waymo for the first time08:52 The algorithm ding09:59 Invisalign enters the chat10:41 Claude Fable returns nerfed13:32 AI regulation gets messy18:44 AI tools and IP risk22:33 Taste as a moat gets challenged25:02 Breaking down types of taste27:40 Timing, novelty, and AI trends29:53 Trend cycles hit warp speed31:12 AI slop can damage brands34:45 Vintage aesthetics and timing38:37 Taste needs systems now40:14 Evolving visual taste43:19 South Park and imperfect taste45:55 Figma updates and custom tools52:39 Shaders, motion, and Weavy56:01 Retention beats acquisition01:00:59 Adobe Firefly Foundry01:02:25 Disney enters custom AI models01:03:34 The custom model problem01:07:09 Midjourney preview mode01:08:18 Midjourney V8.2 texture and skin detail01:16:13 Midjourney V9 training and web redesign01:16:43 Midjourney editing roadmap01:21:34 Secret search tip01:23:03 Broken toes and podcast lore01:25:14 Listener shoutouts01:27:13 Subscribe, hype, tell a mechanic#FastHours #ArtificialIntelligence #AI #AICreative #GenerativeAI #AIArt #Midjourney #ClaudeAI #AdobeFirefly #Figma #Weavy #AITools #BrandStrategy #CreativeAI #AIWorkflow

Midjourney's Wildest Move Yet: Full Body Medical Scans

Midjourney spent years helping people generate impossible images. Then it used that image money to build a machine designed to look inside the human body. In Episode 71, Drew Brucker and Rory Flynn, two men with zero medical degrees and a medically concerning level of confidence, unpack Midjourney Medical and David Holz’s surprise hardware reveal. At the center is the Midjourney Scanner, a water-based, full-body Ultrasonic CT prototype designed to capture detailed 3D body maps in roughly 60 seconds. They break down how the scanner uses sound waves, water, and serious computing power; why Midjourney plans to introduce it through a San Francisco spa; and how a bootstrapped company with no investors can make a bet this strange. They also separate the scanner’s current body-composition ambitions from the much bigger MRI-level future Midjourney hopes to pursue through research, testing, and FDA approval. Then the episode gets even less normal.Claude Fable 5 appears, dramatically accelerates Rory’s coding, Blender, and MCP workflows, and disappears days later following a US government directive. Naturally, this sends the hosts directly into Conspiracy Corner with no adult supervision. Along the way, Drew and Rory explore how brand adoption of AI has changed, why some of the most advanced commercial AI work stays hidden behind NDAs, how companies can reward employees for useful AI innovation, and why first-time reaction content remains one of the internet’s strongest viral formats. Is Midjourney’s full-body scanner a medical breakthrough, an ambitious wellness experiment, or the first clue to a much larger hardware roadmap? The hosts attempt to answer that question while also discussing the World Cup, the Knicks, government intervention, possible AI futures, and several topics their wives wisely avoid asking them about. --- ⏱️ Fast Hour 00:00 Knicks, World Cup, and viral tourism 10:14 Sports, culture, and AI gatherings 13:06 Midjourney reveals secret hardware 15:49 David Holz explains the bigger mission 18:27 The 60-second full-body medical scanner 20:18 How bootstrapping made this possible 23:26 Water, spas, and medical skepticism 28:56 The scanner demo and nine-person team 40:30 Midjourney’s bigger secret roadmap 48:11 How brand AI adoption has changed 58:57 Claude Fable 5 appears, then vanishes 1:00:41 Inside the Fable 5 conspiracy corner 1:04:48 Why Fable 5 felt revolutionary 1:13:58 The AI race and 12 possible futures 1:18:22 Four years of Midjourney and the outro

The Weird AI Video Formula Getting Millions of Views

In Episode 70, Drew Brucker and Rory Flynn are joined by Tyler Bernabe, better known as jboogxcreative, a full-time generative AI creator, strategist, and social menace responsible for some of the wildest AI videos your algorithm has probably shoved into your face at 1:13 a.m. They get into how Tyler has gone viral across multiple generations of AI tools, why copying trends is creative quicksand, how shock value actually works when it is paired with taste, and why the best AI creators are building formats instead of chasing them. The conversation also goes deep into the unglamorous machinery behind creative internet magic: Instagram to Patreon funnels, ManyChat, six-hour livestreams, creator burnout, client work, taste, consistency, and why “just post more” is advice usually given by people who should post less. Then things get properly nerdy. Tyler breaks down his current AI creative stack, including Midjourney 8.1, Seedance, Claude, YAML-style video prompting, Nano Banana, GPT image editing, Kling, Artcraft, Venice AI, Magnific/Freepik Spaces, Weavy, Reeve 2.0, and the never-ending wait for a proper Midjourney editor. Along the way, they cover Chinese prompt translation for Seedance, 10,000-character prompt workflows, reference image construction, anime style development, mood board blending, why AI should sometimes pull you away from your own creative bias, and why the smallest edit in AI video still feels like defusing a tiny cursed bomb. ⏱️ Fast Hour00:00 Fast Hours welcomes Tyler aka jboogxcreative01:51 Going viral through every AI era02:35 The anatomy of scroll-stopping AI03:07 The seductive food video origin story05:32 Running opposite the AI meta08:24 Is AI art? Tyler’s best answer10:35 Why clients pay for your thing12:10 Stop copying other creators17:11 Viral views vs real conversion22:03 Building a creator business solo26:28 Burnout, longevity, and going through it33:05 Tyler’s current AI tool stack38:15 Artcraft, Seedance, and Chinese prompts42:05 Claude, YAML, and 10K prompts50:44 Tyler’s reference image hack58:15 Dream sketches and creative prototyping01:04:10 Reve 2.0 and layered editing01:10:38 Waiting for Midjourney’s editor01:16:02 Closing thoughts #FastHours #jboogxcreative #AIVideo #AIArt #GenerativeAI#Midjourney #Seedance #ClaudeAI #AICreator #AIWorkflow #ContentCreation #AIPrompting #CreatorEconomy #AIAnimation#CreativeAI

Google Dropped Too Many AI Tools. Which Ones Matter?

Drew and Rory are back for episode 69, which is legally required to begin with at least one immature joke before immediately collapsing under the weight of Google’s latest AI product avalanche.This week, they dig into Google Omni, Gemini 3.5 Flash, Google Flow, Google Pics, Nano Banana, Veo, and whatever else Google launched before anyone had time to make coffee. The big question: are these actually meaningful creative upgrades, or did Google just throw 19 AI names into a blender and call it innovation?They break down early Omni and Flow tests, why video physics still feel weird, where Seedance and Kling may still be ahead, and why Runway Aleph 2.0 feels promising but imperfect. Rory shares hands-on examples with character swaps, driving videos, golf swings, agent mode, and Flow’s new tool-building features. Drew tries to keep the conversation coherent while quietly wondering if every AI product now needs a map, glossary, and mild sedative.The episode also gets into Gemini as a search replacement, creepy context awareness, privacy tradeoffs, AI tools connecting to personal data, the fuzzy definition of “agentic,” the limits of auto-clipping tools, GPT Image 2’s SynthID watermarking, metadata headaches for client work, and the universal pain of wasting $15 trying to make an image model spell “stump.”If you’re trying to understand what Google’s AI updates actually mean for creators, marketers, AI video workflows, image generation, creative direction, and the future of agentic media tools, this episode is half useful breakdown, half group therapy for people with too many tabs open.---⏱️ Fast Hour00:00 Cold open00:32 Google’s AI naming avalanche01:39 AI hype vs actual workflow value02:34 Why AI launches feel like iPhone upgrades06:12 Google’s “throw everything” strategy07:08 Omni vs Veo 4 expectations07:43 Video physics and speed problems09:03 Google Pics, Flow, Omni, and Flash10:04 How Rory actually uses Gemini11:51 Gemini 3.5 Flash breakdown12:38 AI benchmarks feel like marketing13:42 Gemini as a better search layer15:18 Creepy Gemini context awareness17:35 Why AI data connections feel too early19:15 The privacy tradeoff gets darker21:19 Google Omni vs Runway Aleph 2.022:12 Google Omni testing starts rough23:39 Google Veo 3.1 feels forgettable25:21 Why Omni feels early26:19 Higgsfield clipper test fails27:59 Why auto-clipping still misses31:30 Rory tests Flow and Omni live32:41 Omni character swap struggles33:33 Runway Aleph panda test34:07 Flow’s new interface and tools35:02 Building custom tools inside Flow36:10 The joy of making tools from nothing37:39 Agent mode for still-image workflows39:05 Batch creative directions in Flow40:03 Omni turns six images into video40:47 Driving physics still feel off41:55 Why consistency matters for adoption43:03 Kling, Seedance, and the update race43:59 Seedance handles complex camera motion45:42 GPT Image setup for golf video46:53 Testing the same prompt in Flow49:25 Why agentic platforms can feel thin51:10 The need for visual design systems52:21 Flow’s golf swing result53:56 Everyone is racing toward agentic54:18 What “agentic” actually means56:03 Claude feels more genuinely agentic57:04 Josh Hart quote analysis detour58:44 Reverse-engineering creative patterns59:53 Pizza, calzones, and prompt structure01:00:26 SynthID and GPT Image 2 watermarking01:01:47 Metadata problems for client work01:02:51 Google Pics enters the chat01:04:03 Too many image models to track01:04:52 Midjourney color still hits different01:06:01 GPT Image 2 quality frustration01:06:59 Image models still struggle with scale01:08:26 Bad AI weeks happen too01:09:20 Midjourney 8.2 speculation01:10:01 Tell your florist

• Transcript

The Prompt Is Dead, Long Live the Reference + The Monet Trap

In episode 68 of Fast Hours, Drew and Rory return from a two-week hiatus to prove that yes, the AI news cycle did continue without their permission. Rude. They dig into Freepik changing its name to Magnific, why enterprise AI image tools are starting to feel more like creative operating systems, and how brands may be better off using approved model aggregators instead of building weird internal Franken-tools that immediately become outdated. Then things get nerdier. Obviously. Rory breaks down how he’s using Codex, GPT-Image-2, Claude Code, MCPs, Higgsfield, Seedance, and visual style reference sheets to create repeatable image systems, character references, and bulk creative workflows without living inside a giant text prompt forever. Drew pushes into where Midjourney V8.1 still dominates, especially photorealistic faces, color, texture, and images that do not look like corporate stock photography that lost the will to live. They also talk about Midjourney’s upcoming 8.2, 8.3, V9 roadmap, edit model ambiguity, personalization drift, Luma Uni comparisons, Pinterest’s internal AI image model, Salesforce going headless, and why AI video audio still sounds like it was recorded inside a cursed podcast booth. And because no episode is complete without accidentally getting philosophical, they close with the viral Claude Monet AI social experiment, the weird bias people bring to AI-generated images, and why “how it was made” keeps hijacking whether people can actually see what’s in front of them. Basically, it’s an episode about the future of AI creative tools, with two guys trying to sound calm while the ground turns into soup beneath them. -- ⏱️ Fast Hour 00:00 Cold open01:12 AI news fatigue is real01:44 Claude Code runs the day now03:11 Remote work and coffee shop crimes08:21 3 Ninjas nostalgia break10:09 Freepik becomes Magnific11:47 Why Magnific works for enterprise13:00 Model aggregators vs internal tools18:01 Pinterest builds its own AI image model22:11 Salesforce goes "headless"24:08 Higgsfield, MCPs, and Meta ads29:51 Codex for GPT-Image-2 workflows32:45 Pulling style from video frames34:05 Building visual style reference sheets37:36 Codex and textured illustration systems39:34 The evolution beyond text prompts41:50 Seedance storyboards and visual prompts43:01 Reference images as reusable seeds44:51 AI video still has an audio problem46:13 Audio reference hacks in Dreamina50:52 Omni-reference for video control52:37 Midjourney V8.1 updated take53:28 The blue and pink problem returns55:37 Midjourney still owns realistic faces58:56 Reworking old prompts with Describe01:01:10 Luma Uni vs Midjourney color01:02:11 Midjourney 8.2, 8.3, and V901:03:46 Midjourney edit model questions01:07:13 Midjourney plus Seedance films01:09:03 Midjourney’s strange lane01:12:28 The Monet AI social experiment01:15:13 Why people over-detect AI01:20:09 AI backlash and disclosure debates01:22:50 AI as a career unlock01:24:30 Keep making weird stuff01:25:45 Wrap-up and seamstress CTA

• Transcript

GPT Image 2 Is Good. But Is It Nano Good?

Fast Hours has entered the witness protection program. Same Drew. Same Rory. But fewer syllables and more chaos.In this episode, Drew Brucker and Rory Flynn officially drop “Midjourney” from the podcast name and relaunch as Fast Hours, a broader home for the creative AI ecosystem: image models, video models, LLMs, vibe coding, Claude, ChatGPT, Midjourney, and whatever tool drops five minutes after they hit publish. Naturally, the rebrand lasts about four minutes before they’re elbows-deep in GPT-Image-2, OpenAI’s new ChatGPT image model that quietly showed up and immediately started making designers question their calendar, career choices, and relationship with kerning.The big topic: GPT-Image-2 is shockingly good with text, typography, brand systems, visual decks, product mockups, and multi-image outputs. Rory walks through how he used ChatGPT and Claude to create a custom typeface from visual references, generate a premium typography presentation, extract geometry, and turn the whole thing into usable font files. Drew then shows how he turned his own handwriting into a working typeface, because apparently “personal brand” now includes making your lowercase g file a tax asset.They also dig into the uncomfortable middle ground of AI creative work: when it saves time, when it still needs human judgment, why anti-AI panic and AI hype both miss the point, and why the real advantage is context. Not prompts. Not magic buttons. Context.The episode also covers GPT-Image-2 vs Nano Banana Pro, richer color rendering, micro-text improvements, AI-generated sports graphics, brand kit concepts, Freepik settings, Claude Design, 4K video generation, Kling, Veo 3.1, Seedance, and the strange reality that a custom brand typeface can now go from “that’ll be $150K” to “Rory did it before lunch.”Basically, it’s an episode about the exact moment creative production stops feeling like a tool demo and starts feeling li ke a factory someone accidentally left unlocked.---⏱️ Fast Hour00:00 Fast Hours is (re)born03:36 Going tool-agnostic04:34 GPT-Image-2 quietly drops05:31 Text becomes the unlock07:31 The AI backlash returns10:57 Hype, fear, and the middle12:10 Typography gets weird14:50 What custom fonts cost15:43 GPT-Image-2 vs Nano Banana17:39 Rory’s font experiment18:47 Fiddleheads become a typeface19:39 Building the type deck20:36 The nine-slide image unlock21:14 Geometry, spacing, and logic22:11 Turning images into font files23:02 Micro-text gets better24:19 Claude builds the font package26:41 The revision loop changes27:50 Context is the silver bullet32:11 Drew makes a handwriting font35:35 Why designers obsess over type37:52 Reverse-engineering prompts39:51 Richer color and sports graphics41:27 Fixing artifacts and details42:37 Nano Banana vs GPT-Image-2 tests44:26 Sports realism gets scary good45:27 Why teams need this now46:43 Freepik settings and ratios48:36 Testing, tokens, and limits49:44 Brand kits and rebrand concepts53:19 Google I/O and the next model53:48 Veo 3.1 falls behind55:04 Kling adds native 4K56:40 Character sheets and macros58:07 Rebrands as visual prototypes01:00:53 Building a reference library01:01:36 Three weeks in a row01:02:58 Claude Design tease01:03:37 Tell your local [fill in the blank] spam finale

• Transcript

Midjourney V8.1 Review & Reactions + Wen Edit Model?

Midjourney finally dropped v8.1, so Drew and Rory did what any responsible adults would do: generated way too many images, argued with style codes, stress-tested text, and immediately started asking whether the edit model is the part that actually matters.In episode 66 of Midjourney Fast Hours, the boys dig into why Midjourney v8.1 feels way better than v8, where it still falls short, and why this release feels less like a victory lap and more like Midjourney finally arriving at the version v8 probably should’ve been in the first place. They get into faster generations, native 2K output, mood boards, prompt depth, describe, personalization profiles, text rendering, image weight, --exp behavior, old v6 style-code weirdness, and the growing sense that the real make-or-break feature is still the edit model.They also get into how Midjourney stacks up against tools like Nano Banana, Grok, Reve, and Luma, why image generation still feels fragmented across platforms, and whether Midjourney should even bother chasing video or just go all-in on images, editing, and control.Then, because this is still Midjourney Fast Hours, the episode somehow ends with a deeply important discussion about custom Mac folder icons.If you care about Midjourney v8.1, prompting strategy, style references, AI image workflows, generative art tools, or where Midjourney is actually headed next, this one’s got the goods.---⏱️ Fast Hour00:00 Intro and v8.1 arrives01:05 Is v8.1 actually better than v8?04:09 The edit model is the real test06:22 Should Midjourney even chase video?10:07 v8.1 needs more prompt depth12:07 Mood boards feel usable again14:28 Testing the new describe tool21:00 Personalization profile matters most22:09 Text tests and object recognition23:57 “Photo” vs art and stylize tests29:54 Why v8.1 feels a bit like v630:43 Old style codes hit differently now42:08 --sv7 issue and style-code confusion45:47 Missing parameters and what still works47:26 Hidden text tests and image weight49:57 --exp tests and behavior shifts52:35 Grid view and the alpha site54:50 Office Hours, 8.2, and edit timing01:03:27 Custom Mac folder icon detour01:09:01 Wrap-up and parting nonsense

• Transcript

Claude Knows Kung Fu. Midjourney's Still in the Dojo (+V8.1?)

In episode 65, Drew Brucker and Rory Flynn return for another round of Midjourney Fast Hours and immediately do what they do best: poke at bleeding-edge AI tools until something breaks, gets weird, or accidentally becomes useful.They kick things off with fresh Midjourney V8 impressions, including what changed after another week of testing, why resetting personalization profiles helped, where the weird magic still shows up, and why V8 still feels like it is waiting for its real arrival. They also dig into the rumored Midjourney V8.1 update, what it could fix, and why the real test may come down to the edit model, text rendering, consistency, and whether Midjourney can pull serious users back into the platform.Then the episode takes a sharp turn into Claude, and honestly, this is where things get deliciously nerdy. Drew and Rory unpack how they are building with Claude in real life: when something should become a skill, how Claude MD files shape everything downstream, why auditing your own setups matters, how to think beyond rigid workflows, and what happens when your AI starts feeling less like a chatbot and more like a strange little operating system trained on your habits, instincts, and creative baggage.They also get into edge-case detection, memory files for collaborators and clients, private repos, Codex as backup muscle, analogy engines, and a growing obsession with building a “creative intelligence layer” that can carry more of his actual thought process into AI tools. ---⏱️ Fast Hour00:00 Intro and the boys are back01:12 Why the podcast got bigger than Midjourney03:25 Rory’s updated Midjourney V8 take04:40 Why new personalization profiles helped06:31 The weird Midjourney magic is back13:24 Midjourney 8.1 might be the real V816:36 Why the edit model really matters18:51 Claude skills: what should be a skill23:58 Why Claude MD files matter so much25:23 Building flexible AI systems, not rigid ones38:38 Rory’s edge-case detector skill41:55 Memory files for people and projects43:48 The creative analogy engine50:35 Why examples beat vague prompting53:38 Back up your Claude brain immediately55:30 Rory’s orchestrator and skill roster01:06:04 Hard-coded flows vs flexible AI judgment01:07:43 Building a creative intelligence layer01:18:01 William Shatner, Babe Ruth, and better analogies01:20:53 Outro and comment bait

• Transcript

Midjourney V8 First Impressions + Claude Code Breakthroughs

Drew and Rory crawl back from travel chaos, token addiction, and mild creative delusion to answer the question everyone’s been asking: did Midjourney V8 finally land... and was it worth the wait?In this episode, they break down their real first impressions of Midjourney V8, including what feels better, what feels busted, why mood boards are suddenly acting possessed, and why the old “short and vibey” prompting style may have quietly lost its crown. They get into coherence, SV6 vs. SV7 behavior, stylize weirdness, failed generations, the alpha-site disappointment, and the one thing that actually matters now: whether Midjourney can ship a truly usable edit model before everyone wanders off to easier tools.Then the conversation mutates into a full-blown Claude Code spiral. Drew and Rory unpack the Chrome extensions, internal skills, markdown systems, Notion setups, custom workflows, and tiny automations they’re building at an alarming pace. There’s talk of AI writing detection, reusable agent pipelines, presentation hacks, Pinterest utilities, GitHub repos, and the growing suspicion that the real side effect of Claude Code is not productivity. It is total psychic collapse with excellent output.If you care about Midjourney V8, Claude Code, mood boards, AI image generation, prompt structure, creative workflows, Chrome extensions, automation systems, or what happens when two visual AI nerds disappear for a few weeks and come back with opinions, this one’s for you. -- ⏱️ Fast Hour 00:00 - Midjourney V8 finally lands 01:25 - Rory’s travel chaos and failed gens 05:06 - First impressions and alpha letdown 11:30 - V8 coherence and vibey prompts 13:30 - SV6 vs SV7 mood board test 21:44 - Mood board degradation gets real 25:56 - V8 looks better, but fails too often 33:04 - Structured prompting may matter more 35:29 - Q4, HD, and stylize confusion 39:09 - The real missing piece: edit model 43:45 - Why nobody wants workaround theater 48:04 - The strange realism hiding in V8 54:45 - Claude Code takes over their brains 58:19 - Rory’s skill stack and agent hub 01:04:15 - Drew’s “ghost system” for writing 01:07:07 - Killing Calendly with Claude 01:11:17 - Tiny tools, huge leverage 01:17:13 - Ask the model how it wants data 01:26:31 - Billboard shout-out 01:32:32 - Wrap-up, RIP Sora, subscribe

• Transcript

Midjourney V8 Countdown + Kling 3.0, Seedance 2.0 & Higgsfield Fallout

After a brief hiatus, the boys are back! With Midjourney v8 expected next week, Drew and Rory zoom out and ask the bigger question: does v8 even matter as much as we think? Because while everyone waits for v8, Kling 3.0 and Seedance 2.0 are raising the bar, Claude Code and Claude Cowork are quietly changing how builders operate, and Claude Agents are turning workflows into autonomous systems. Meanwhile, Higgsfield is melting down in public, Hollywood is panick-maxxing, and creators are realizing that building “skills” inside LLMs might matter more than generating prettier images. This episode breaks down: • Why Midjourney v8’s native 2K and edit models matter• Why personalization could be the real differentiator• How Claude Code is quietly enabling operator-level leverage• Why skill-building beats agent hype• What Kling 3.0 and Seedance 2.0 signal about video AI• The real lesson behind Higgsfield’s fallout• Why the creative skill gap is widening right now This episode moves from Midjourney roadmap analysis to AI workflow engineering to business survival strategy. If you care about Midjourney v8, Claude Agents, Kling 3.0, Seedance 2.0, system prompts, autonomous workflows, or where creative leverage is actually going… This one isn’t optional. --- ⏱️ Midjourney Fast Hour 00:00 – Winter chaos & NYC survival03:59 – AI’s quantum leap moment06:51 – Radio vs podcasts analogy08:55 – AI series vs Hollywood model10:59 – Game of Thrones AI sequel14:14 – CGI patchwork & filmmaking16:14 – AI replacing exec decisions18:03 – Seedance & model hype19:48 – Midjourney v8 timeline20:15 – Rating party (Round 2 + beyond)23:18 – 2K native resolution talk24:26 – Batch-four replacement25:48 – Edit model improvements26:14 – v8 text rendering progress27:03 – Arbitrary resolution support29:06 – Personalization in v830:36 – Mood boards as leverage32:18 – AI overwhelm & X fatigue34:12 – Claude agents & automation36:04 – “Something is happening”39:45 – AI skill-building strategy45:47 – Pattern matching workflows48:54 – Silicon Valley middle-out50:24 – Claude comedy experiment53:24 – Word clouds & ad thinking55:14 – Hollywood recycling IP58:41 – Marketing narrative engine01:03:57 – Higgsfield controversy01:11:36 – Final thoughts & sign-off

• Transcript