Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

liuliu.me

Post reply on HN
Print view View original

81–90 of 184 posts

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#81

Post by tomcam »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

> and generates abominations

You make it sound like that’s a bad thing

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#82

Post by frankzander »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

Nothing. It's IMHO just a hype of the younger nerdy generation. The real world applications of NN-based (there is no I in A) image generation are limited. One hype comes the other hype goes. IMHO it did not come to stay ;-)

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#83

Post by nelsondev »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

Play around with other prompts. For example, “golden gate bridge in the style of Van Gogh futuristic”.

Architecture is cool. It doesn’t do people well

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#84

Post by dt3ft »

tomcam wrote: post #81
dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

> and generates abominations You make it sound like that’s a bad thing

Horror movie material for sure :) Who knows, maybe this inspires better horror movie creatures :)

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#85

Post by pdntspa »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

try some of the prompts listed on lexica.art. Stable Diffusion needs good prompt engineering to turn out well

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#87

Post by dave_sullivan »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

It's more of a cool technology that is rapidly advancing. A couple years ago, it couldn't do this much. A couple years from now, it will be much better. It does much more than mash images together, which you would know if you dug into it a bit. That's it, that's the whole thing.

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#88

Post by cdrini »

dt3ft wrote: post #80

Congrats on the release! I gave this and other available applications a try and I don’t understand what people see in ai image generation. A simple prompt generated a person with 3 nostrils, 7 squished fingers, deformities everywhere I look, it just mashes a bunch of photographs together and generates abominations. Pay close attention to generated models and you will find details which are simply wrong. What is the u…

I can't speak for others, but I've personally been quite impressed by the dalle output. It creates things that would take me hours (if not days) to create, which no other tech I've tried has been able to generate. It feels like it can absolutely replace at least the stock photo industry. It's also terrific for things like blog photos if you don't have the time or talent to create something yourself, but want some creative control.

Expansions like dream booth, which let you fine tune the system with your own submitted images are also quite amazing. Being able to give it just a few photos, and say things like "show me surfing in the ocean" and get a reasonable image back.

_Much_ more broadly, this space in AI/ML with GPT3/Dalle is exciting because it feels kind of like what the internet was made for. There's too much data on the internet for any one person to ever meaningfully process. But a machine can. And you can ask that machine questions. And instead of getting just a list of references back, you get an "answer". Image generation is the "image answer" part of this system. It's an exciting space because it feels like these systems will affect large chunks of how we use computers.

Here's a cool GPT3 "programming" example: https://twitter.com/goodside/status/1581805503897735168

And here are some of my dalle uses I've been impressed by, that I feel is publish-ready:

- https://labs.openai.com/s/nkOTLRWzjgQTe4QsgoWChP7n

- https://labs.openai.com/s/uSP55qRf1SqCbYTa2UDXXEfA

- https://labs.openai.com/s/kO2purvEodK5UUxPIpL78bQh

- https://labs.openai.com/s/2P1Mb75JbS1mmpyi86xwyyUg

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#89

Post by donlinglok »

WantonQuantum wrote: post #2

This is cool and looks like a great way to drain my phone battery :) I just used the prompt "A person looking at their phone in amazement" and got a good picture. Beware that on startup the app downloads almost 2 gig of data.

I have generated some images, I think it only takes less than 1% of the battery for an image, this is already much better than most of the game(for having fun).

Re: Stretch iPhone to its limit: 2GiB Stable Diffusion model runs locally on device

#90

Post by gorbypark »

burk96 wrote: post #21

This looks so cool! Unfortunately, my 16.1 11pro is crashing before an image can be generated, let me know if I can do anything to debug/test this.

It’s working fine on my iPhone 11 Pro / iOS 16.1 with all default settings. Just generated an image of an astronaut skiing that looks pretty good!
Post reply on HN