I'm building my personal home right now. The AI image models have been a game-changer in designing the look of the house. My architect did an OK job, but the details that Nano Banana added really bring the house up a notch. I just do hundreds of renders from the basic 3D models and I find looks that I like and iterate from there. We are implementing the renders from Nano Banana over our Interior Designers designs. We would not have hired the Interior Designers again after using Nano Banana to do our interiors.
I think part of the issue with architects and designers today is that they use CAD too much. It's easy to design boxes and basic roof lines in CAD. It's harder to put in curves and more craftsman features. Nano Banana's renders have more organic design features IMO.
Our house is looking great and we're very happy how it's going so far with a lot of the thanks to Nano Banana.
Part of the job of interior design is delivering the promised images in … yknow, physical reality? How are you going from nano banana images to actual plans, materials, finishes, products, paint codes, … ?
Interesting. I model interior architecture as "here's $xxxK, make it nice" and they do a bunch of work to figure out what you mean by nice, and a bunch more work to codify your definition of nice into, like, SKUs of sconces and so on. Seems like NB helped you figure out your definition of nice, and your subcontractor had a good designer on staff to execute on that.
A sufficiently detailed render won't require a designer to figure out the materials. Any (reasonably competent) contractor can take a sufficiently detailed render with him to the store and find matching products. At least assuming the thing in the render actually exists.
He can also send back a picture of the real product for approval. I think the primary difference here is the level of involvement. A quick consult and then the professional "makes it all work" versus hands on design with the client figuring out all the details for himself.
What a laughably elitist attitude. Contractors are perfectly capable of obtaining materials on your behalf. Although these days it often makes more sense to place online orders yourself.
There's nothing wrong with hiring an interior designer to handle all the work for you. The important thing to realize here is that modern generative image models have significantly reduced the barrier to managing these things for yourself.
Not everyone can afford the best interior designers, my sister had hired one to design the interiors of her new cafe.. the designer did not provide any renders, just a basic CAD drawing. Then I used nano banana pro to create some renders from the photos of the empty space. These turned out great, and she decided to ditch the designer and use the designs created by nano banana. The cafe has opened now, and it looks great!
not the op, but this is what i did too and bypassed the designer. I iterated with nano banana and gave the result to the company that builds the kitchen. the middleman is gone now.
A designer knows things from experience and would be aware of small details that if not designed correctly, become very apparent when built in reality.
The interior designer doesn't really do squat. They can do plan drawings and have some off the shelf cupboards and furniture. They don't implement anything
NB Pro can do some seriously impressive edits around interior decorating - see the prompt that replaces the window with a mirror which correctly reflects the room. It's not perfect, but it's still damn impressive.
I'm deeply impressed, especially with the "replace window by mirror". It did not only do the window thing right, it also changed the illumination of the whole room while keeping all the other details unchanged.
Right? That part kind of blew my mind too - the multimodal model actually altered the overall lighting in the room by eliminating all the reflections and specular highlights when the natural light was taken away WITHOUT being asked in the prompt.
Yeah it's not perfect though I'll have to take your word for it - I looked up the concept of "bokeh swirl" but didn't really understand it in the context of the image.
To me it looks like the two foreground subjects (fox and girl) are at roughly the same distance from the POV camera and thus NB Pro tried to preserve an approximate narrow depth of field on both of them, but I'm not a professional photographer by any means.
Same! I redid my backyard entirely and needed ideas. Gemini took a pile of dirt and gave me countless ideas, improved my plans, recommended materials, etc. a designer gave me two out of the box ideas that Gemini didn’t come up with, but it did everything else perfectly. (Designer said, put a patio out in the yard and put your table there, and take your ugly shed and make it the center of attention, since you’ll never succeeed trying to hide it)
Same thing here. I took a picture of some gravel/grass and asked it to show me what it'd look like with tiles. I showed it another part of the property, and asked it to show me what it would look like with a raised lawn. Super impressive to be able to see a cloudy idea in the physical realm like that.
This was a year ago so I used a lot of different models, if I did it now I’d definitely just use nano banana. Just test and see what works, but IMO take pictures from where you’ll physically be most often and optimize for the view from that location. Ie my dining room table opens to the yard, so I sat at the table, took a picture of the yard, and had ai work through that to start.
Can you write a bit more about your workflow? I've been thinking about doing the same, but since I'm very non-interior-design minded have struggled to ask the right things.
Like...
What are your inputs to the model? Empty renders of the space, or more fully decorated views/ photos?
Do you have a light harness around this to help you discover the style you like and then stay consistent with it?
Do you find that giving a lot of context around the space you're designing helps (it hasn't in my attempts)?
I started with sketchup to make basic floor plans and house shapes. I had a rough idea of the style of the home. I picked "Transitional English Estate" since the build site is out on a farm that sorta looks like the Cotswolds. I used AI in this process to get rough renders and feedback on the floorplan. I then took that basic floorplan and house dimensions to a Draftsman who did a lot of tweaking to get it up to code and fix issues. I got his plans and took it to a Sketchup Pro on Fivver . They made a detailed sketchup model. I then took that model and took screenshots from different perspectives and tweaked the prompt to get renders I liked. These changes were reencorprated into the blueprints. I did the same thing with the interior. Took screenshots from sketchup and put them into AI and tweaked the prompt. https://imgur.com/a/lSIYTYr
Mine was far more lightweight, but u just uploaded pics of my yard and prompted manually a bunch of times. Sometimes id find reference images to give as context, draw on the image to call out specific areas, etc.
It wouldn’t show me the exact things I wanted, but got close enough that I could test ideas and iterate quickly.
I actually built an app to accomplish this exact thing as I was finishing building my home and was clueless when it came to interior design. I'm genuinely astonished by the capabilities of these models with regards to this, and it feels vastly underutilized by the general populace. Being able to try out multiple paint colors in seconds, or add real furniture or wall decor from Ikea, or move objects around instantly - it still blows my mind.
The cost of doing more complex designs is analogous to the cost of doing more complex builds.
If you can afford the extra cost for someone to figure out how to build the blue sky designs that nano banana spits out, maybe you can afford something more thoughtful and interesting than a shitty mashup of other peoples mcmansions.
Out of curiosity: what is your input to the model? A CAD file or a drawing?
I find it does a good job at isometric views from floor plans. However, I needed Gemini 3.1 Pro to be able to have a chance at rendering 3D human point of view images from floor plans.
Any chance you'd be willing to share an album? I've considered doing this for my own home and I'd be psyched to study practical examples. Honestly this would make one helluva blog post (imo).
Is any of this intrinsically a strength of Nano Banana, while not of other models/generative tools? Have you tried doing the same with say Klein, ZIT, etc.?
Nano Banana was the first generative image tool that seemed to understand architecture. I have some 18th century engravings that I've been trying to get AI tools to visualize as though they were photographs of real structures, and the results were comically bad until Nano Banana came along. I remember seeing the announcement, dropping a sketch into Gemini with the prompt "Make this a photo" and it preserved all the features and dimensions, but added photorealistic textures.
I still do a lot of modeling of historical buildings in Sketchup and Twinmotion, but Nano Banana has really helped me with more easily visualizing a world before photography.
I think part of the issue with architects and designers today is that they use CAD too much. It's easy to design boxes and basic roof lines in CAD. It's harder to put in curves and more craftsman features. Nano Banana's renders have more organic design features IMO.
Our house is looking great and we're very happy how it's going so far with a lot of the thanks to Nano Banana.