top | item 35616264

Reroom AI: Test interior design ideas and styles before hiring a designer

66 points| eddieweng | 3 years ago |reroom.ai | reply

52 comments

order
[+] btbuildem|3 years ago|reply
It looks more like it's re-skinning a room/space rather than trying different design ideas - all the elements remain where they are, but are restyled.

I think a big contribution of an interior designer is their ability to see potential in a space and reorganize it in a way that works better for a purpose / feels better to be in. This in comparison seems "skin deep"

[+] eddieweng|3 years ago|reply
Hi, thanks for the feedback. The upcoming version will allow you to modify results using prompts.
[+] blensor|3 years ago|reply
This looks to be stable diffusion with controlnet. Since many of the original lines are kept it is probably Canny Edge or HED. That's why it looks so similar to the original room.
[+] anton001|3 years ago|reply
That’s unfortunate: https://imgur.com/a/3x5axjl
[+] jakear|3 years ago|reply
I love how people will a) criticize OpenAI/etc. for restricting access to models and "aligning" their output, and b) immediately leap to shaming models that aren't "aligned".

Not just you, it's all over this thread.

[+] dragonwriter|3 years ago|reply
Race transformation aside, I particular find the “floppy sock” => “deformed foot” modification to be…an interesting choice.
[+] nicpottier|3 years ago|reply
Ooof. Maybe as a first pass it should check for people in the photo and just stop if there are any.
[+] knolan|3 years ago|reply
Just for fun I uploaded a screenshot from Cyberpunk 2077 because I was trying out the new path tracing update.

https://imgur.com/a/UpD9kHs

It’s fun to see how it deals with UI elements.

[+] janmo|3 years ago|reply
90% of what is generated is not doable.

You cannot just add a new window like that, or change the view you have. Also the furniture that is generated doesn't exist as it is generated as well, so how are you actually supposed to buy it?

[+] eddieweng|3 years ago|reply
Hi, thank you for your feedback. Currently, the product is intended for inspiration purposes only.
[+] jakear|3 years ago|reply
Take the designs to a craftsman? If AI inspires a resurgence in craftspeople using their skills to create truly bespoke pieces, that'd be a very good thing.
[+] iacomus|3 years ago|reply
Do a reverse image search on Google and buy the closest matching piece of furniture. Doesn't have to be precisely the same
[+] karaterobot|3 years ago|reply
Cool way to imagine a room in a different way, and get ideas for a mood board you can hand to a designer. Of course, most of the stuff it imagines does not actually exist, and could not be purchased off the shelf. You'd need a lot of custom cabinetry and furniture work, next to which hiring a designer in the first place would probably not be much of an expense.
[+] non-|3 years ago|reply
This tool is cool but my biggest takeaway is that the key to attractive interior decor is better lighting.
[+] capableweb|3 years ago|reply
Light in general is a huge asset when wanting to change the aesthetics of anything really, people really underestimate the impact of light.

Game looking a bit boring? Improve the lightning, instantly better

Boring photos of people? Consider how the light traverses the scene you're capturing, and they become much better

Bathroom looking dull? One well placed lamp can change it entirely.

Want to make cool professional videos? Purchase one nice production lamp and you're like 90% there already.

[+] nostromo|3 years ago|reply
I love it!

It'd be nice if there was a way to say what is and is not changeable.

For example, I noticed it usually improves the view outside of the windows to be beautiful vistas -- not something you can do without moving. Being able to request that other things not change, like the floor plan or the flooring for example, would be nice.

I like how the AI will randomly turn furniture into a dog, as if to say, "improve this room with a furry friend." :)

[+] eddieweng|3 years ago|reply
Glad you like it! I understand your point; I'll work on object segmentation and let users decide what to change. Thanks for the feedback
[+] mavsman|3 years ago|reply
Tried it on my basement and the generated picture wasn't even close to relevant. I think the issue was that I have a ton of junk in my basement and the generated image had no idea about what was junk and what was important in the room. It closed off a window, made my ceiling taller, and added a giant window in a place where it's just not possible.
[+] narush|3 years ago|reply
Cool! Just tried it out with my partner (in the process of designing their living room in a new place).

UX suggestion: let me select a new style without having to re-upload the photo. We wanted to check out a bunch of styles on the same photo, but doing so took 10 clicks instead of just 1!

[+] eddieweng|3 years ago|reply
Thank you for the feedback! will implement this feature for sure
[+] nicpottier|3 years ago|reply
This is wild, do you mind sharing what the process is in broad terms? I'm super impressed!
[+] eddieweng|3 years ago|reply
Yes, certainly. The image generation process utilizes a variation of the text-to-image model called StableDiffusion. The frontend collects requests and sends them to a two-layered backend. The first layer determines the appropriate prompt to send to the worker, while the second layer calls the image generation API. Once the image is generated, it is sent back to the first layer and then returned to the client.
[+] TheObviousOne|3 years ago|reply
Seems like pretty basic prompts...

Nothing special that are not already have seen on the internet :(.

[+] swader999|3 years ago|reply
Time to add this to my block list. Can't have the wife stumbling upon this.
[+] howon92|3 years ago|reply
Is this just a SD model with ControlNet with interior-design-specific prompts?
[+] extr|3 years ago|reply
Really cool. My girlfriend is into interior design and I've been showing her projects like this as they come along: in her view these are some of the best results yet. A few first impressions though:

- They need to add a filter to the uploaded images (or at very least curate the front page), maybe some kind of classifier that determines if people are in it. This kid [1] is all over the examples if you click "load more". Absolutely hilarious, but I'm sure not what they're going for.

- The model loves to change "boring" exteriors into scenic vistas. Brick wall? -> Cityscape. Trees? -> Ocean view. Yes, that does improve the room, but I'm not sure moving your room to beachfront property or up 40 stories is practical for most people.

- The model seems to have a bias towards making rooms darker. Dark/moody scenes are usually not how designers choose to show off their work, or what most people want.

[1] https://imgur.com/0qKi5ZY

[+] eddieweng|3 years ago|reply
Hi, thanks for the feedback! NSFW image filter will be added into the pipeline, and the upcoming version will allow you to modify results using prompts.
[+] nextworddev|3 years ago|reply
At a first glance, seems to blow interior ai out of water by a big margin
[+] mdrzn|3 years ago|reply
Are all the creations automatically shared on the homepage?