Kitchen Renovation ideas animation using Stable Diffusion [video]
youtube.comUsing stable diffusion to generate and walk through different kitchen renovation ideas. 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. Yeah, that's what I saw too, a digital mood board with blobs of abstract kitchen-like things that you could theoretically cut and paste the parts you like onto a digital whiteboard. Once that part was done, then the designer could use those bits and pieces to identify what you like best and cross reference that with what is available and what is possible within your budget and get you the result that you would be happiest with. With that, the actual designer is still a very important piece of the puzzle and this does very little to replace them. The images definitely look good enough to serve as ideas/inspiration IMO. A sketch doesn't need to look photorealistic to inspire you. But at that point does it need to be your room even? If the results aren’t actionable because of constraints, why not just flip through images of existing real world kitchens? Well yes a double sink and a six top cooking space look great on brochures but it's only when you try to fit the fridge, the window and that awkward door that you realize you'd end up with a single 60cm working space or the corner element won't open or the dish washer door interferes with the fridge door or walkable space or you can only open drawers standing on their side GP was talking about inspiration. That doesn’t mean you get to carbon copy anything. When the AI blows away support walls and rearranges things that can’t structurally work, its utility is limited too. It can also dream up sinks/fridges/ranges that don’t exist with sizes that aren’t realistic either. I’m supportive of the general direction but in a model that’s built for it where all the real constraints can actually be accounted for reliably. That would allow you to go beyond looking at pics for inspiration into renderings you can flip through easily. Bonus points if it can approximate cost, including plumbing and electrical in rearranging things for where plumbing and electrical already are. It doesn't look like this stable diffusion would be able to tell you that either. You can see it changing the shape (angles) of the room in real time. It does not show cabinets at real depth etc. Correct. In a different field, we're using AI to do the same thing but for streets: https://twitter.com/betterstreetsai ...and it's already led to actual change: https://twitter.com/MikeBradleyMKE/status/157083982421467545... 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. >“uncanny valley” isms 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. Did you watch the video?? Yep. I forgot to add that on this imaginary blind test, the ai images would have to be hand selected to avoid these "transitory" frames where things get blurred and joined. Seriously??? I'm not talking about "transitory" frames. I'm talking about things like the bottom of the top kitchen cabinets frequently being missing, top beams being at different levels in an impossible "MC Escher"-like configuration. I definitely could see this being useful in plugging in different "styles" to decide what you like, and then taking that to a designer or architect to build out a real design, but anyone paying attention should easily be able to identify the generated images. Now you gave some characteristics to pay attention to, and that's fine, but it's not exactly an "uncanny valley", is it? At least that does not elicit the same effect on me as when I see a CGI of eyes in a super-realistic 3D render of a person. I could totally see myself missing these details and misjudging images like these as human-generated. Maybe I'm just not an attentive person. So you are basically proving OPs point. If a human has to hand curate computer generated images then the computer isn’t taking the place of a designer/general contractor/architect anytime soon. I never said AI-generated images would take the place of human professionals soon. I asked what exactly "uncanny valley" isms mean. Uncanny Valley is a term to describe things that look mostly correct, but are "off" in a way that triggers an alarm in most human brains. 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. that is super cool you are in that industry, any thoughts on a tool that assists interior design teams/architects on this kind of ideation? It has the potential to retire the average salaryman in the creativity field (not just interior design teams/architects but specially UI/web designers). Outliers will be outliers and choosing one may give the client an edge but the average creative may not do much better than this "AI" and as such loose the ability to put bread on the table doing "creative" work. As someone in my field (radiology) has put: It's not that doctors will be replaced by AI, doctors using AI will replace those who do not. Do you think it's gonna be a tool used by these "average teams" or like a standalone self-serve product without any service human involved? I'd bet on a former, but why do you think? One thing I'd say as a UI/Web designer is that often you are responding to a unique set of requirements to a specific brand / use case / functionality. I can 100% see how tools like this will influence and redefine the idea phase of a project but at the moment I can't see how it will make the leap from something that looks like a fuzzy representation of an end product to something that IS the end product. outliers don’t always start out as outliers though, it’s a skill that needs development usually 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 > "more like this", "less like that" I wonder if those could be implemented as vector addition in the latent space. 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. > This is still rehashing the same concepts/ideas in circulation not producing novel ideas or innovating in this space. That's exactly what the average creative professional does. As an anecdote, being intellectually honest, most of the architects I know (and I know many as an housing architect myself), would not do better than this tool does now - "creatively" speaking - let alone in the future. I'm also curious how non-novel this is. Ie if A and B are both pre-existing individually, A+B might still be reasonably novel. Which may be a bad thing honestly. This will do some things where a seasoned designer would avoid for a technical limitation. Ie A and B shouldn't be combined for some logical reason, where as maybe StableDiff would just throw pieces together without care. But still, StableDiff has been amazing in my view. Prototyping anything this quickly is going to be a game changer. As someone who doesn't think in pictures well, this looks to let me mock things up so incredibly well. I am so hyped for the refinement of the tooling in this space. Seems like a valid point, but aren’t 99.999% of kitchen remodels rehashing the same ideas and concepts in circulation? 99.999% of clothes? 99.999% of furniture? This wasn't a value judgement BTW. I acknowledged the valid and productive use cases for this project but pointed out that it wasn't revolutionary in creativity or innovation at this stage. For me, it looks like Pinterest on steroids, very capable and efficient but not mind-blowing or out of this world. Novel innovative kitchens are not something people want. They want it to be a kitchen. 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... HNs version of ads I fixed it for you Well sir, I think we should remove the ceiling and add another row of windows to the kitchen. Thoughts? This is really nice, but there are some funny things suggested that might not be too easy to realize: 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. Nice, a short how-to writeup on this (even on Youtube description for video) would be good. 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 ? Anyways, fascinating. 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. You are probably not going to get Stable Diffusion to spit out a picture of a car by feeding it pictures of horses. However, we should not neglect small incremental innovation that is created by combining previously known knowledge in new ways. 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. This link from a few days ago lets you provide the seed image. Same issue though, it may suggest you remove your ceiling or move a door. I let it generate the initial start image, but I could see how another option would be to guide it with an initial real photo. that would be cool too. Isn't this like InteriorAI by Pieter Levels? You can add your own seed image in that one but it's monetized. I love how part of it starts making me feel like the kitchen is slowly imprisoning me with less and less space. It’s an apt analogy for chasing perfection and being trapped on the hedonism treadmill. SD is great now to be "creative". It would be 1000% more useful if we can give it a few constraints and still be "creative". [video]? hi labria, click on the title of the post to view the youtube video they are simply saying the title should warn users that it is a video and don't click with your mic unmuted while in a meeting :) oops my bad! I love how it just decided in the middle you should just move the kitchen to outside i also love how there are a few frames where it has 2 or 3 dish washing machines. i need that in my life. I have an aunt who, when she was renovating the kitchen and discovered how much custom cabinets cost, had a second dishwasher installed instead. It didn't cost much more and now she has a cabinet that can also clean the dishes as well as storing them. I mean.. not wrong? How come this submission is a link and has text at the same time?