Veo 3 Makes Yesterday’s Best Look Like a Beta Test + Runway & Midjourney Check-In

May 26, 2025

Dive into the latest in AI with a look at Google's intriguing Flow suite and its new Veo 3 video model. Discover why Midjourney still feels like magic in a sea of products with confusing names. Get insights on pricing strategies and the evolution from Veo 2 to Veo 3. Plus, enjoy discussions on 3D modeling, interior design innovations, and the practicality of generative AI. Expect fun value tips, resource management hacks, and creative ideas that might just inspire your next project!

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Google's Data-Driven AI Surge

Google's Flow Suite integrates advanced AI tools including Veo 3 for video and Gemini for images, pushing creative boundaries.
It leverages massive data from Google and YouTube, giving it a data advantage few can match.

ADVICE

Conserve VO3 Credits Wisely

Start video generation with VO2 or quality mode before upgrading to VO3 to save modest credits.
Use VO2 for prompt testing to conserve your expensive VO3 credits effectively.

INSIGHT

Veo 3's Video Realism Leap

VO3 impressively captures complex video coherence including camera motion and facial expressions in generated scenes.
This exhibits AI's advancing ability to understand and generate nuanced physical and emotional cues.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Midjourney Fast Hours, Episode 40

After a short hiatus (blame conferences and caffeine dependency), the Rory Flynn and Drew Brucker break down Google’s shiny new Flow suite — with its Veo 3 video model, sound + dialogue generation, and confusing-as-hell product naming. They talk strategy, cost, coherence, and why it still feels like Midjourney has that “magic dust” no one else can replicate.

Along the way: Runway love, layering hacks, JSON secrets, interior design with arrows, and 3D dogs with job titles. It’s fun. It’s weird. It’s chaotic. But you’ll probably walk away with 3 ideas you want to try right away.

Also, someone paid $125 just to tell you whether it's worth it. (You're welcome.)

---

Midjourney Fast Hour

0:00 – When did this madness begin?2:19 – AI video is finally getting spicy3:29 – Google’s Flow Suite: Veo 3, sound, and coherence5:02 – Google's confusing product soup: Flow, Gemini, Imagen, Whisk10:45 – Pricing pain: Is Veo 3 worth the $125?13:09 – Veo 2 vs Veo 3: Best value tips and tradeoffs15:08 – Prompt accuracy and physics: Is Google really listening?17:53 – Why less prompt effort = better results now19:40 – Veo 3 vs Kling vs Midjourney: Prompting philosophies20:52 – Scene builder: Longer takes and smart extension workflows22:34 – The catch: extending drops quality and loses sound24:17 – New image-to-video support + third-party images25:41 – Ingredients-based generation and persistent characters27:10 – Frame extraction: finally, a feature we all needed28:08 – Timeline editing, upscaling, and staying inside the tool29:48 – Sora vs Veo 3 vs Runway: usability and consistency31:43 – Canva, Figma, Framer: Tools are becoming monsters35:33 – Figma’s new AI website builder is wild36:40 – Prompting sneaker ads and JSON-based design37:09 – Why training teams on AI is almost impossible38:07 – Hedra who? Veo 3 makes fast pivots a must39:55 – Midjourney's next move: what video could look like41:11 – Runway’s underrated features and clever reference hacks44:26 – Scene sketching and layout prompting: mind blown47:25 – Interior design from mood board to layout to render49:45 – Lighting direction via floorplans = next-gen hack52:53 – Try-on tech and Chrome extensions54:22 – Style consistency with JSON + ChatGPT58:23 – Mass-generating stylized icons and dogs with jobs1:02:36 – Midjourney updates: V7.1, personalization, and video1:05:01 – What Midjourney must get right with video1:07:18 – The one-shot window to impress1:09:23 – Bring back the Midjourney magic1:11:14 – Wrap-up: chaotic times, coherent thoughts, caffeinated takes