@mountain_mal @NanoBanana For generating 360 images 1K is practically useless and 4K is taking too long. Wish they would allow for custom output sizes so we can optimize for quality vs time
English
thameem
337 posts
@th2049 @NanoBanana correct - 4k was taking just over a minute for me
English
a bunch of you said this would be huge for real estate 🏡
so i pushed it further: virtual staging just went 3d 👀
the flow:
1. capture 16 ultra-wide photos
2. stitch into a 360° equirectangular panorama
3. feed that into @NanoBanana with a staging prompt → generate a newly staged 360° image
4. reconstruct that into a fully navigable 3d world using @theworldlabs
you’re not just staging photos anymore -
you’re staging space
i’m starting to think 360° panoramas might just be the bridge between 2d and 3d worlds
edit the pano. edit the world.
Martin Maly@mountain_mal
i built an app that converts any space into a digital clone in minutes as the founder of Teleport - the only iphone app that can capture high-quality 360° panoramas - i already had the perfect input when @theworldlabs released their 3d reconstruction api 📍 first test - a co-working space in chiang mai 🇹🇭 the flow: 1. capture 16 ultra-wide photos 2. stitch into a 360° equirectangular image 3. reconstruct a fully navigable 3d environment via @theworldlabs api there’s something profound about exploring these 3d worlds. it brings you back in a way photos never could.
English
@th2049 @NanoBanana very cool! I agree that the loading time isn't ideal, but it's still significantly faster and cheaper than physically staging a home. right now I'm using gemini 2.5 flash image which takes ~15 seconds to generate the edited version
English
@SanjanaBandara @mountain_mal @NanoBanana I remember having the same issue. I can’t remember how I solved it off the top of my head since it was a while ago. I’ll check and let you know.
English
@th2049 @mountain_mal @NanoBanana amazing, i'm working on a similar concept.
How did you get ultra-wide camera working with gyroscope tracking? ARKit won't force ultra-wide, and AVFoundation + CoreMotion breaks my alignment detection. Do you have any tips?
English
English
@jaloxin @mountain_mal @NanoBanana Its just a prototype for now. Stopped working on it after I realized it takes around 90s for image generation with nano banana. Waiting for a faster image gen model to be released 😅
English
@mariosaputra How???? Clean up derived data, preview caches, simulator data, old installations if they are there.
You’ll bring it down to like, 10-15 gigs TOPS
English
thameem retweetledi
“I want to make beautiful things… even if nobody cares.”
— Saul Bass
English
thameem retweetledi
Saw 3 people kill iPhone apps on a one-hour train ride 😩
Apple should fix this and clarify when an app should be force quit (i.e only if it’s unresponsive or not working as expected).
Antoine v.d. SwiftLee @twannl
Stop killing your apps — you’re not saving battery, you’re draining it. 🪫
English
@gamedevmayank @MattCowlin For me the warning message disappeared after saving. Maybe it would be different if your app age rating needs to change to comply with the new rules?
English
@MattCowlin So basically, it should go through a review with a new version? I checked on the official page and they just mentioned save it, after that there's no clarification (whether to submit for review or not)
English
You can only do this if you have a new version waiting for any kind of submission
If you only have 1.1 READY FOR DISTRIBUTION
and no
1.2 PREPARE FOR SUBMISSION for example, you need to add a new version
Viktor Seraleev@seraleev
Two days ago, Apple sent developers an email with a pretty alarming subject line: Final Reminder. In it, they reminded everyone that the updated Age Rating questionnaire must be completed by January 31 To make things easier, here’s a quick step-by-step guide: 1. You don’t need to submit an update 2. Create a new version of your app 3. Go to App Information 4. Scroll down to the Age Rating section and tap Edit 5. Answer the updated questions and hit Save That’s it – your app is now fully compliant with Apple’s new requirements
English
@MattCowlin I was thinking of doing something similar a while back. What do you think is the main benefit of this approach?
English
I’ve found a good system with a “co-founder” if you can call him that 😉
We both make apps and split everything, doubles our chances at success and fun to have another person to work with and bounce ideas off
Mario Saputra@mariosaputra
The reason I don't want a cofounder is that I don't want long term commitments. I also don't like the idea of splitting revenue, as it adds complexity. I prefer to pay someone to handle a specific task and move on.
English
we used to design UI in a professional photo editing tool
we forgot how to make this
English
thameem retweetledi
Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask:
"What do you think about xyz"?
There is no "you". Next time try:
"What would be a good group of people to explore xyz? What would they say?"
The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".
English
English
If I hit this dictation button after sending a text and it beeps and stops my music one more time,
I’m gonna find everyone at apple and put them in a rear naked choke hold
Even if I turn off dictation I somehow hit the voice note thing
The send button should not have multiple functions in the same spot
English