
5 steps to generate consistent brand images with Midjourney
Jamey Gannon (guest), Claire Vo (host)
In this episode of How I AI, featuring Jamey Gannon and Claire Vo, 5 steps to generate consistent brand images with Midjourney explores a repeatable Midjourney workflow for consistent, on-brand image systems The episode focuses on consistency: moving from one-off “cool” Midjourney generations to a coherent brand image library by using a tight, repeatable workflow.
A repeatable Midjourney workflow for consistent, on-brand image systems
The episode focuses on consistency: moving from one-off “cool” Midjourney generations to a coherent brand image library by using a tight, repeatable workflow.
Jamey starts with mood boards (Pinterest/Cosmos), then shifts to style references (SREFs) to better control color/contrast and avoid Midjourney “averaging” effects.
She adds personalization codes (profiles) and selective prompting shortcuts (editorial/publication names, “luxury,” camera models) to quickly dial in a distinctive, scalable aesthetic.
Finally, she packages the system for clients (prompts, profiles, references) and uses Nano Banana/Flora as “Photoshop” for targeted fixes like upscaling, swapping objects, and face/pose composites for thumbnails and content.
Key Takeaways
Consistency comes from a process, not clever prompts.
Jamey emphasizes a “tight and manicured” workflow so you’re not endlessly prompting; the goal is repeatable inputs (references, profiles, minimal text) that reliably yield a coherent set.
Get the full analysis with uListen AI
Use mood boards to define taste, then prefer SREFs for control.
Midjourney mood boards can “average” a mixed vibe; dragging the same images in as SREFs often produces stronger, more predictable carryover in color/contrast/camera treatment.
Get the full analysis with uListen AI
Diagnose what’s ‘overpowering’ and remove or crop it out.
If an element dominates (green eyeshadow, bubblegum), don’t fight it with long prompts—remove that reference or crop the distracting region and re-run to keep the composition without the unwanted cue.
Get the full analysis with uListen AI
Develop a small set of reliable test prompts to audit a style quickly.
Prompts like “ethereal female model,” “astronaut,” “cats,” or “runner” are broad enough to reveal how a style applies across textures and subjects, helping you spot mismatch early.
Get the full analysis with uListen AI
Personalization codes add ‘your lens’ but require careful curation.
Profiles trained via rapid A/B voting can add crispness and modernity, but “style bleeding” happens if you like too many images with a secondary art style (e. ...
Get the full analysis with uListen AI
Use high-signal shorthand words to specify setting and style.
Names like “Dazed editorial,” “Vogue,” or a camera model can encode many visual decisions at once; similarly, “luxury” implies penthouse/high-rise cues without verbose scene description.
Get the full analysis with uListen AI
Treat Nano Banana/Flora as production polish, not core generation.
Midjourney is for fast ideation and consistent systems; use Nano Banana like “Photoshop you can talk to” for targeted swaps (e. ...
Get the full analysis with uListen AI
Notable Quotes
“It all comes down to having a very tight and manicured process… so you're not pulling your hair out prompting all day.”
— Jamey Gannon
“A picture is worth a thousand words. Like, literally a picture to an LLM is worth a thousand words.”
— Claire Vo
“Mentioning, like, Vogue or high fashion… is a great way to tell the model a ton of stuff without actually having to tell a ton of stuff.”
— Jamey Gannon
“Nano Banana… literally is just Photoshop. That's exactly how you should think of it.”
— Jamey Gannon
“Firstly, take a break, always.”
— Jamey Gannon
Questions Answered in This Episode
When do you decide a mixed-vibe mood board is “too averaged” and it’s time to switch to SREF-only—are there specific failure signals you look for (contrast, palette drift, camera treatment)?
The episode focuses on consistency: moving from one-off “cool” Midjourney generations to a coherent brand image library by using a tight, repeatable workflow.
Get the full analysis with uListen AI
How many SREF images do you typically start with, and what’s your rule for adding/removing references without introducing chaos or “too Midjourney” busyness?
Jamey starts with mood boards (Pinterest/Cosmos), then shifts to style references (SREFs) to better control color/contrast and avoid Midjourney “averaging” effects.
Get the full analysis with uListen AI
Can you share your go-to “test prompt suite” (e.g., astronaut, cat, runner) and what each one reveals about a style’s strengths/weaknesses?
She adds personalization codes (profiles) and selective prompting shortcuts (editorial/publication names, “luxury,” camera models) to quickly dial in a distinctive, scalable aesthetic.
Get the full analysis with uListen AI
For personalization codes: what’s your recommended voting strategy (skip rate, session length, number of ratings) to avoid accidental style bleeding?
Finally, she packages the system for clients (prompts, profiles, references) and uses Nano Banana/Flora as “Photoshop” for targeted fixes like upscaling, swapping objects, and face/pose composites for thumbnails and content.
Get the full analysis with uListen AI
How do you choose between (1) cropping an image reference, (2) removing a SREF, and (3) using Midjourney’s “no” parameter or Nano Banana edits for unwanted elements?
Get the full analysis with uListen AI
Transcript Preview
It all comes down to having a very tight and manicured process, which thankfully I have spent my 10 gajillion hours in Midjourney and Nano Banana everything to figure out exactly what that is, so you're not pulling your hair out prompting all day.
One of the things I like about the mood board is it's a visual language to explain to Midjourney what you're trying to do. The picture is worth a thousand words. Like, literally a picture to an LLM is worth a thousand words.
Mentioning, like, Vogue or high fashion or even, like, a different artist's name is a great way to tell the model a ton of stuff without actually having to tell a ton of stuff.
In the past, brand and creative directors or agencies will give you these photos and be like, "Cool, call us and re-up when you want more photos." What I love is that you're like, "Look, you're gonna value me for all this upfront work that I'm gonna do to define the space, give you these codes, really give you reference images, and then now you can go do this for yourself." It's just, like, a very different model of providing service, and I think it creates a really positive collaboration between the client and the creative director. [upbeat music] Welcome to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today we have an aesthetic episode with Jamey Gannon, who is an AI creative director, and is gonna show us how to create consistent, beautiful, and unique brand assets using Midjourney, Nano Banana, Flora, and more. This is a workflow we haven't seen yet, and goes into incredible depth on how to create awesome brand assets that you can use to uplevel all of your designs. Let's get to it. As an AI founder, you're used to sprinting towards product market fit, your next round, or that first enterprise contract. But speed isn't enough for AI startups. Buyers expect security, compliance, and transparency from day one. That's why serious AI startups use Vanta. With deep integrations and automated workflows built for fast-moving AI teams, Vanta gets you audit ready fast and keeps you secure with continuous monitoring as your models, infra, and customers evolve. AI innovators like LangChain, Writer, and Cursor scaled faster and closed bigger deals by getting security right early with Vanta. Listeners can claim a special offer of one thousand dollars off Vanta at vanta.com/howiai. Jamey, thanks for joining How I AI. I am having you on the show for a very selfish reason, which is I think I'm the only pink AI brand in all of SaaS, and when I saw your work, I was like, "Oh my God, I need this lady to teach me how to create brand imagery that is beautiful and fun and girly, and whatever magic she has, I need." So talk to me about how we can get amazing images like what you're showing us right now. I think consistently is, is the most important part, 'cause I can get a one-off image that's this great, but I can't get this brand portfolio. So you gotta tell me your sorcery.
Install uListen to search the full transcript and get AI-powered insights
Get Full TranscriptGet more from every podcast
AI summaries, searchable transcripts, and fact-checking. Free forever.
Add to Chrome