GUEST · EP 049 MARCO ISLE

Marco Isle

Creative polymath with a background in graphic design, UX/UI design and fashion

On Fast Hours August 31, 2025

Episode 49 thumbnail: NANO BANANA MADE ONE IMAGE A STORYBOARD
Episode 49 AUG 31 2025 · 70 min

Midjourney Token Bashing, Nano Banana, and Weavy with Marco Isle

ft. Marco Isle

Episode 49 pairs Rory and Drew with creative polymath Marco Isle to pressure-test Midjourney prompting and Google's Nano Banana image model. Marco demonstrates token bashing, fusing two prompt words into one, and his custom GPT for extracting reusable tokens from reference images, while Rory shows a Weavy-automated workflow that turns a single Midjourney product photo into a full multi-angle, multi-variant shoot via Nano Banana. They also weigh Nano Banana against Flux, Runway, ChatGPT and Veo 3 for consistency.

  • Token bashing fuses two prompt words into one novel term (like 'illumination' + 'provocation'): Marco says it unlocks results a structured prompt wouldn't find.
  • Shoot a subject from front, side and rear three-quarter angles first: that reference set lets Nano Banana generate any new angle without morphing.
  • Rory automates the whole shot list in Weavy: drop in one reference image and the flow outputs front, side and rear variants with zero manual prompting.
  • Rory calls Flux 'flat' with no depth, and says ChatGPT image gen is stuck at roughly 3:2 crops; both lose to Nano Banana on control.
Open the episode

Marco Isle, on the record

“And then I was playing with like this experimental thing where you like fusing some of the words together because obviously an LLM doesn't look at text how humans look at it.”
Marco Isle Ep. 49 Why token bashing works: LLMs don't parse text like humans do Play from 13:26
“My default is just like mid-journey for exploration because nothing even comes close to it … Never will. It's just game over.”
Marco Isle Ep. 49 Why Marco still uses Midjourney over rivals for exploration Play from 37:53
“Diving into not only the work that we create, but then looking at influences and then putting those into the GPT, extracting tokens and then messing with them. It's infinite, right? It's an iterative process that will probably never end.”
Marco Isle Ep. 49 Marco's iterative process: extract tokens from influences, then remix Play from 34:31