I read a lot of these posts on stable diffusion, midjourney, etc., and I don’t want to fall into the classic “I don’t think this is ready yet” camp, but one thing an Architect will be able to do really well which these tools won’t is make a kitchen that is actually usable. I mean, this thing is basically a corrupted Pinterest of kitchen ideas with doors and drawers intersecting, beams that make no sense, and flooring that looks menacing. And until we have AGI I don’t think our program sophistication will be able to iron out these “uncanny valley” isms that seem built into every aI image generation tool.
Now I know that this tool is just a “starting point” for using as ideas, but I have seen way more fabulous (and sane) kitchen designs en mass on houzz, dezeen, basically any online blog. The technology is cool, but it seems limited. As in we can only get weird amalgams of human concepts. All this to say, I work with architects professionally, and I do not see this as something that will cause their field concern in the near to mid term. These programs cannot make drawings with structural suggestions, floor plans for the layout they produce, or anything else that a person pays an architect for. Just my two cents
This isn't meant to be a literal blueprint maker- it's an idea machine. The advantage of Stable Diffusion is that you can put an actual photo of your real life kitchen in as a seed, and see the ideas applied to your space. It's not the same as browsing through pictures of kitchens on pintrest or houzz, which show entirely different locations of different sizes, different lighting conditions, or different dimensions; it's hard to imagine or apply those ideas to my space if my space is radically different. My kitchen is a small apartment kitchen with a single window and a narrow space, it isn't analogous to 99% of the posts I saw scrolling through houzz just now. But if I could upload a picture of it and see 5-10 new cabinet arrangements or designs, I might be inspired by one and use it as a jumping off point for a new setup.
Someone with zero design experience could run this over a photo of their kitchen and realize that their exact real world kitchen would look nice with a different set of paneling, or a different set of chairs, or a larger window, etc. Obviously they have to consult with an architect or other expert to see how feasible larger renovations are, it's not meant to replace architectural work, but there is plenty of value already added as an inspiration tool. In fact it might lead to a lot more work for architects, if they can use a tool like this to show potential clients a bunch of inspiration for how their kitchen could look, without doing any actual architectural work up front.
I will suggest that in a critical way, none of us, you included, "know" that this is a starting point.
So much of the reaction and subsequent reasoning about such tools is bounded (predictably, inevitably, naturally) by human cognitive error—in particular, our total collective inability to reason with non-linear extrapolations.
We "know" this is a starting point, but even the linear line from "nothing like this existed at the start of 2022" to now, projects into a "what exists in 18 months" which is itself an effectively instant timescale (residential A&D projects here in SF are often 3-year endeavors...)...
...what this looks like for a loose interpretation of "this," is literally unimaginable to us.
One technical thing: I was just telling someone 30 minutes ago, in the lats week, my #aiart timeline and feed on Twitter started saturating this week with extrapolations into AR/VR applications.
The toolchains which will exists in this domain prior even to the launch of Apple's long rumored AR goggles are already eyebrow-raising. Assuming there is a path to deploy experiences onto Apple glass, there's going to yet another infusion of energy (cough money) into the precambrian explosion going on around ML/imagegen etc.
Don't make the mistake of thinking flaws in proof-of-concept first-passes like this (which is already IMO quite compelling for ideation), are going to be a permanent fixture or blocker.
If you review the evolution of imagegen over the last two years, you can get a taste of how ephemeral most such limitations are...
...and the egregious ones tend to attract a frenzy of work.
To put a point on it, I think you're OK saying "near" term, but "mid"... absolutely not. This is just one more place where disruption is clearly visible on the horizon.
I don't think there's any need to be shy in saying this only looks cool but it's completely useless. The "starting point" for using as ideas already exist - it's the data this has been trained on.
This is not going to replace architects or designers in the near term, but it could still transform the industry.
The conversion pipeline for things like this today relies on ads, word of mouth, and expensive sales processes. Imagine a homeowner uploading a photo of their kitchen and being shown hundreds of possible redesign styles. The homeowner can choose one to start a conversation with a designer. That pipeline will convert way more people than the status quo, and the industry as a whole will grow.
> Now I know that this tool is just a “starting point” for using as ideas, but I have seen way more fabulous (and sane) kitchen designs en mass on houzz, dezeen, basically any online blog.
Somehow I doubt those blogs have the same floor plan as my house or any easy way to filter for things that would fit in my own kitchen. Don't underestimate the power of seeing a design in your exact kitchen/space. What looks good in one layout isn't guaranteed to look good in another.
> All this to say, I work with architects professionally, and I do not see this as something that will cause their field concern in the near to mid term. These programs cannot make drawings with structural suggestions, floor plans for the layout they produce, or anything else that a person pays an architect for.
Ok but that's not the point, at least it's not for me. I'm not trying to replace architects, I'm trying to figure out what I want so I can take it to someone who knows better and say "I want this". They can kick back anything that's not going to work structurally but I kind of doubt this is going to be a big problem as, not to be an ass but, I have a brain. I know where the cabinets can go (the same place my existing ones are) along with my sink/oven/dishwasher. What I'm looking for is designs/colors/etc and how that would look in my kitchen, I'm not designing a kitchen/house from an empty plot of land.
As with all Stable Diffusion (and most AI stuff, see CoPilot) the goal (or at least my goal) isn't to replace the designers/architects/programmers/etc but to automate away the parts that waste a bunch of time. For CoPilot that's boilerplate or similar code blocks, for this it's letting me see designs and (hopefully) tweak or re-gen parts I don't like until I get it close enough to take it to an expert. I fully understand the "kitchen remodel" tool doesn't exist today but it's not hard to imagine what it would look like with image input, in/out-painting regions, and a nice GUI wrapped around a Stable Diffusion core.
What exactly does that mean? I bet most people would fail to tell things apart on a blind test comparing kitchen designs generated by humans vs. ai (not counting the "transitory" images with blurred corners etc.). Same thing with concept art.
As an (housing) architect this is simultaneously amazing and terrifying.
In some way, stable diffusion works like the architect mind that has seen more kitchens (in this case) than the average person and somehow (consciously or unconsciously) proposes a solution based on that. Our edge - for now - is knowing what is feasible/economical.
Once we can do "more like this", "less like that" in a way that doesn't require a 3 paragraph inscrutable word soup for prompts, I don't see how this doesn't revolutionalize most industries that need any type of quick prototyping of anything.
You could do this for any sort of web / mobile / whatever UI, designing houses, cars, any object really, fashion, etc. It's all going to be so much faster.
I think its either a simpler program with a phrase database, or another AI, that all serves as an abstraction to understanding prompt sections to steer Stable Diffusion
This is still rehashing the same concepts/ideas in circulation not producing novel ones nor innovating in this space. Maybe it will prove beneficial for rapid prototyping during the ideation stage for mass-market products/services in the commercial/residential remodeling industry but nothing revolutionary.
I've been playing with something similar and it's pretty fun.
Take a picture of a room then use img2img in stable diffusion automatic1111.
Set denoising strength to a value between 0.3 and 0.6. Lower than 0.3 and not much will change, higher than 0.6 it tends to start changing the whole room.
It can be used without a prompt or use a prompt to attempt to describe the room, like a "a living room with a grey couch a white table walls with wallpaper" then change parts of the prompt to morph it in desired direction, like add a chair something or add the name of art styles or "by someartistname". Just having a prompt that somewhat describes the room and pressing generate many times will also just create a lot of random alternative interiors, like in the video. If you want to create a video I guess you'd use deforum, but I haven't really tried that.
The stuff documented under img2img alternative test here can also be useful if you manage to dial it in properly. This is for keeping the image more stable and getting more control of what you change.
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki...
I like this idea but I would suggest that you invest some time in some UX validation if you want to maximize the potential usage.
I own a SaaS that offers online 3D configurators for outdoor structures [1] since 2014, and tried something similar as a UX experiment a couple of years back; here is the gist of it:
We offered 20 different variations on the screen at the same time, and people had to gradually fine-tune their preference by clicking on the one they liked the most.
I tested this in the field, and it proved to be very confusing to the end-user, unless you highly constrain the amount of parameters that can change at the same time, and describe to the user what changed and go step by step.
In the end I decided to ditch the whole idea in favor of a hard-coded step-by-step wizard where users can adjust the relevant parameters themselves one by one, which tends to work the best for the majority of the users.
=> My suggestion for you would be to do something similar: highly constrain the potential changes, and guide your user step by step. If you manage to do this, I think you might have gold in your hands.
I would also love to challenge the naysayers who say the generated images don't make sense: in my opinion it will only be a matter of time before someone starts training or hardcoding a classifier that invalidates "wrong" images.
(Especially if one would be able to generate a reasonable 3D representation of the image without too much effort.)
As someone once said in a random AI video on the internet: "Dear fellow scholars, I wonder what we will be capable of just 2 more papers down the line"
[1] ** edit ** removed the URL, check my profile if you really want to know...
And at the same time ... only variation of conformism ?
Stable Diffusion opens a lot a avenues and yet it is somewhat "restricted" to what it "knows/understands". Put differently, if cars it exposed to is black can it paint them pink ? What about even higher level construct ? It can not innovate can it ? Not yet ?
If you go to 95% of architects or interior designers, they will give you designs that are largely representative of current trends, which is incidentally what most people want.
Very few people in creative industries are truly pushing that industry into new frontiers, and that is actually appropriate. Exploring outside the frontier is actually full of failure, and far less likely to produce something most people want.
I honestly think that people operating outside of the frontier of established creative trends technically have a completely different set of skills, and a completely different job altogether, than people who create within the boundaries.
For this particular case I’d want it to be even less creative. I want it to be able to make designs that just use cabinets that are available to buy, and it should know where to source them and what they cost.
And only show me lights that really exist and are for sale, etc.
Did you start with some stock photos? The photos of your kitchen?
There are a lot of changes in the windows and other stuff that is difficult to modify in real life. It would be nice to be able to restrict the changes, but it's probably difficult to "explain" that restriction to Stable Diffusion.
[+] [-] totalview|3 years ago|reply
Now I know that this tool is just a “starting point” for using as ideas, but I have seen way more fabulous (and sane) kitchen designs en mass on houzz, dezeen, basically any online blog. The technology is cool, but it seems limited. As in we can only get weird amalgams of human concepts. All this to say, I work with architects professionally, and I do not see this as something that will cause their field concern in the near to mid term. These programs cannot make drawings with structural suggestions, floor plans for the layout they produce, or anything else that a person pays an architect for. Just my two cents
[+] [-] naet|3 years ago|reply
Someone with zero design experience could run this over a photo of their kitchen and realize that their exact real world kitchen would look nice with a different set of paneling, or a different set of chairs, or a larger window, etc. Obviously they have to consult with an architect or other expert to see how feasible larger renovations are, it's not meant to replace architectural work, but there is plenty of value already added as an inspiration tool. In fact it might lead to a lot more work for architects, if they can use a tool like this to show potential clients a bunch of inspiration for how their kitchen could look, without doing any actual architectural work up front.
[+] [-] aaroninsf|3 years ago|reply
So much of the reaction and subsequent reasoning about such tools is bounded (predictably, inevitably, naturally) by human cognitive error—in particular, our total collective inability to reason with non-linear extrapolations.
We "know" this is a starting point, but even the linear line from "nothing like this existed at the start of 2022" to now, projects into a "what exists in 18 months" which is itself an effectively instant timescale (residential A&D projects here in SF are often 3-year endeavors...)...
...what this looks like for a loose interpretation of "this," is literally unimaginable to us.
One technical thing: I was just telling someone 30 minutes ago, in the lats week, my #aiart timeline and feed on Twitter started saturating this week with extrapolations into AR/VR applications.
The toolchains which will exists in this domain prior even to the launch of Apple's long rumored AR goggles are already eyebrow-raising. Assuming there is a path to deploy experiences onto Apple glass, there's going to yet another infusion of energy (cough money) into the precambrian explosion going on around ML/imagegen etc.
Don't make the mistake of thinking flaws in proof-of-concept first-passes like this (which is already IMO quite compelling for ideation), are going to be a permanent fixture or blocker.
If you review the evolution of imagegen over the last two years, you can get a taste of how ephemeral most such limitations are...
...and the egregious ones tend to attract a frenzy of work.
To put a point on it, I think you're OK saying "near" term, but "mid"... absolutely not. This is just one more place where disruption is clearly visible on the horizon.
[+] [-] trabant00|3 years ago|reply
[+] [-] mgraczyk|3 years ago|reply
The conversion pipeline for things like this today relies on ads, word of mouth, and expensive sales processes. Imagine a homeowner uploading a photo of their kitchen and being shown hundreds of possible redesign styles. The homeowner can choose one to start a conversation with a designer. That pipeline will convert way more people than the status quo, and the industry as a whole will grow.
[+] [-] joshstrange|3 years ago|reply
Somehow I doubt those blogs have the same floor plan as my house or any easy way to filter for things that would fit in my own kitchen. Don't underestimate the power of seeing a design in your exact kitchen/space. What looks good in one layout isn't guaranteed to look good in another.
> All this to say, I work with architects professionally, and I do not see this as something that will cause their field concern in the near to mid term. These programs cannot make drawings with structural suggestions, floor plans for the layout they produce, or anything else that a person pays an architect for.
Ok but that's not the point, at least it's not for me. I'm not trying to replace architects, I'm trying to figure out what I want so I can take it to someone who knows better and say "I want this". They can kick back anything that's not going to work structurally but I kind of doubt this is going to be a big problem as, not to be an ass but, I have a brain. I know where the cabinets can go (the same place my existing ones are) along with my sink/oven/dishwasher. What I'm looking for is designs/colors/etc and how that would look in my kitchen, I'm not designing a kitchen/house from an empty plot of land.
As with all Stable Diffusion (and most AI stuff, see CoPilot) the goal (or at least my goal) isn't to replace the designers/architects/programmers/etc but to automate away the parts that waste a bunch of time. For CoPilot that's boilerplate or similar code blocks, for this it's letting me see designs and (hopefully) tweak or re-gen parts I don't like until I get it close enough to take it to an expert. I fully understand the "kitchen remodel" tool doesn't exist today but it's not hard to imagine what it would look like with image input, in/out-painting regions, and a nice GUI wrapped around a Stable Diffusion core.
[+] [-] subw00f|3 years ago|reply
What exactly does that mean? I bet most people would fail to tell things apart on a blind test comparing kitchen designs generated by humans vs. ai (not counting the "transitory" images with blurred corners etc.). Same thing with concept art.
[+] [-] galfarragem|3 years ago|reply
In some way, stable diffusion works like the architect mind that has seen more kitchens (in this case) than the average person and somehow (consciously or unconsciously) proposes a solution based on that. Our edge - for now - is knowing what is feasible/economical.
[+] [-] albertgt|3 years ago|reply
[+] [-] vasco|3 years ago|reply
You could do this for any sort of web / mobile / whatever UI, designing houses, cars, any object really, fashion, etc. It's all going to be so much faster.
[+] [-] yieldcrv|3 years ago|reply
[+] [-] im3w1l|3 years ago|reply
I wonder if those could be implemented as vector addition in the latent space.
[+] [-] FerociousTimes|3 years ago|reply
[+] [-] macrolime|3 years ago|reply
Take a picture of a room then use img2img in stable diffusion automatic1111.
Set denoising strength to a value between 0.3 and 0.6. Lower than 0.3 and not much will change, higher than 0.6 it tends to start changing the whole room.
It can be used without a prompt or use a prompt to attempt to describe the room, like a "a living room with a grey couch a white table walls with wallpaper" then change parts of the prompt to morph it in desired direction, like add a chair something or add the name of art styles or "by someartistname". Just having a prompt that somewhat describes the room and pressing generate many times will also just create a lot of random alternative interiors, like in the video. If you want to create a video I guess you'd use deforum, but I haven't really tried that.
The stuff documented under img2img alternative test here can also be useful if you manage to dial it in properly. This is for keeping the image more stable and getting more control of what you change. https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki...
[+] [-] ToJans|3 years ago|reply
I own a SaaS that offers online 3D configurators for outdoor structures [1] since 2014, and tried something similar as a UX experiment a couple of years back; here is the gist of it:
We offered 20 different variations on the screen at the same time, and people had to gradually fine-tune their preference by clicking on the one they liked the most.
I tested this in the field, and it proved to be very confusing to the end-user, unless you highly constrain the amount of parameters that can change at the same time, and describe to the user what changed and go step by step.
In the end I decided to ditch the whole idea in favor of a hard-coded step-by-step wizard where users can adjust the relevant parameters themselves one by one, which tends to work the best for the majority of the users.
=> My suggestion for you would be to do something similar: highly constrain the potential changes, and guide your user step by step. If you manage to do this, I think you might have gold in your hands.
I would also love to challenge the naysayers who say the generated images don't make sense: in my opinion it will only be a matter of time before someone starts training or hardcoding a classifier that invalidates "wrong" images. (Especially if one would be able to generate a reasonable 3D representation of the image without too much effort.)
As someone once said in a random AI video on the internet: "Dear fellow scholars, I wonder what we will be capable of just 2 more papers down the line"
[1] ** edit ** removed the URL, check my profile if you really want to know...
[+] [-] naillo|3 years ago|reply
[+] [-] spywaregorilla|3 years ago|reply
[+] [-] jansan|3 years ago|reply
1. Simply remove the ceiling beams.
2. Extend the room and place another window into the wall.
3. Replace wall with window.
4. Cut room in half and replace one part with garden.
5. Open room to garden and slowly extend ceiling into garden.
[+] [-] monkeydust|3 years ago|reply
[+] [-] latchkey|3 years ago|reply
[+] [-] ldng|3 years ago|reply
Stable Diffusion opens a lot a avenues and yet it is somewhat "restricted" to what it "knows/understands". Put differently, if cars it exposed to is black can it paint them pink ? What about even higher level construct ? It can not innovate can it ? Not yet ?
Anyways, fascinating.
[+] [-] ralusek|3 years ago|reply
Very few people in creative industries are truly pushing that industry into new frontiers, and that is actually appropriate. Exploring outside the frontier is actually full of failure, and far less likely to produce something most people want.
I honestly think that people operating outside of the frontier of established creative trends technically have a completely different set of skills, and a completely different job altogether, than people who create within the boundaries.
[+] [-] cookingrobot|3 years ago|reply
And only show me lights that really exist and are for sale, etc.
[+] [-] madsbuch|3 years ago|reply
However, we should not neglect small incremental innovation that is created by combining previously known knowledge in new ways.
[+] [-] gus_massa|3 years ago|reply
There are a lot of changes in the windows and other stuff that is difficult to modify in real life. It would be nice to be able to restrict the changes, but it's probably difficult to "explain" that restriction to Stable Diffusion.
[+] [-] xsmasher|3 years ago|reply
https://interiorai.com/
Same issue though, it may suggest you remove your ceiling or move a door.
[+] [-] albertgt|3 years ago|reply
[+] [-] cercatrova|3 years ago|reply
https://interiorai.com
[+] [-] mensetmanusman|3 years ago|reply
It’s an apt analogy for chasing perfection and being trapped on the hedonism treadmill.
[+] [-] yubozhao|3 years ago|reply
[+] [-] labria|3 years ago|reply
[+] [-] albertgt|3 years ago|reply
[+] [-] xani_|3 years ago|reply
[+] [-] albertgt|3 years ago|reply
[+] [-] nathancahill|3 years ago|reply
[+] [-] ifqwz|3 years ago|reply