Live data from Hacker News

1-Bit Bonsai Image 4B Image Generation for Local Devices

prismml.com

141–150 of 214 posts

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#141

Is there a way to run it on Vulkan?

No. Sadly, NVIDIA killed any kind of compute via Vulkan. I took few minutes to try to make it work on ROCm (AMD's alternative to CUDA), landed in python dependency hell.

> NVIDIA killed any kind of compute via Vulkan

What do you mean? They are the ones introducing the matmul extensions to Vulkan, which makes compute like this possible

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#143

Twenty years ago, I don't think any of us were excited about a future internet where we couldn't trust whether what we were seeing or reading was genuine. I hope one day we'll be able to look back on this era as an aberration, like that scene in Mad Men where the Drapers fling their picnic rubbish onto the grass and drive away.

Twenty years ago my teachers were telling me not to use Wikipedia because you can't trust anything on the internet. You should never date someone you met through an app or website because they are 100% murderers. "The internet is for porn". Things have a way of improving over time, and people always overestimate societal risks of new tech in the beginning.

Young girls suicides, Brexit&Trump (post-truth politics, general democratic decline), demographic catastrophe, obesity crisis are often partially attributed to social media.

Not saying that tech is inherently evil, these could have been prevented, but to me it seems we have underestimated the social risks and failed to regulate accordingly.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#144

Earlier quoted context omitted.

Twenty years ago my teachers were telling me not to use Wikipedia because you can't trust anything on the internet. You should never date someone you met through an app or website because they are 100% murderers. "The internet is for porn". Things have a way of improving over time, and people always overestimate societal risks of new tech in the beginning.

Young girls suicides, Brexit&Trump (post-truth politics, general democratic decline), demographic catastrophe, obesity crisis are often partially attributed to social media. Not saying that tech is inherently evil, these could have been prevented, but to me it seems we have underestimated the social risks and failed to regulate accordingly.

For any new change we underestimate certain risk and overestimate others. This leads to a lot of focus and discussion on the things that don't matter much while the things that do matter become apparent. It's natural, guessing everything about the future correctly is never going to happen, but I don't really think that info tells you things are getting better or getting worse overall - it just tells you what things we focused on instead of should have focused on.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#145
post #32

Genuine question: is this solving a real problem? IME, the bottleneck when using diffusion models isn't storage space or memory, it's generation time. Lots of models will run on 8-12 GB 1080-generation GPUs onwards, or on Macs with similar memory, which are probably the bottom end from a GPU power perspective anyway. I also note that these models are marginally slower than the small FLUX.2 model they're based on. Oka…

> Lots of models will run on 8-12 GB 1080-generation GPUs onwards, or on Macs with similar memory, which are probably the bottom end from a GPU power perspective anyway. Not the bottom end - most people are on laptops or mobile devices that are much lower GPU power than this.

Probably the bottom end an individual would want to consider using due to slow generation time.

Sure, you could theoretically take a model compressed in this manner and deploy it on an old netbook and run the calculations on the CPU, but each image would probably take an hour…

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#146

Earlier quoted context omitted.

Aberration? That seems like an extreme overreaction.

I don't know what else you'd call the widespread and enthusiastic adoption of a technology that is designed to exploit people's trust in the veracity of images by mimicking reality as seamlessly as possible. I think it's both aberrant and abhorrent for the tech industry to be actively developing something that's permanently polluting our information environment. Here's a local story published after I made my comment,…

I think the massive scale up in making bogus images is actually a net good in the end. For decades, even before computers, images were edited on the idea people trust an image. Anything from removing/adding figures to a photo, changing something in the image to modify the meaning, or cropping something out to hide part of it. People had a default trust of images because 99% of the images they saw weren't worth modifying, so they didn't think about it.

Now images have gone back to being like a book. People are beginning to assume anyone can write anything, make up quotes, etc. We still get to keep the ones we just like or the ones we know were really that way (e.g. your wedding vows/wedding photos) but we've dropped this silly notion image=fact just because it's an image. It's not all good that faking an image has gotten consistently easier over the last 100 years, but it's also not bad that it's fallen apart enough people are seeing through it.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#147

Twenty years ago, I don't think any of us were excited about a future internet where we couldn't trust whether what we were seeing or reading was genuine. I hope one day we'll be able to look back on this era as an aberration, like that scene in Mad Men where the Drapers fling their picnic rubbish onto the grass and drive away.

I think it may turn out postive; That the less we are able to take images and video at face value the better.

Motivated actors have been able to doctor, fake, or spin media content since time immemorial. But peoples default mode was to trust what they saw. Now that fake imagery is ubiquitous, maybe we'll all get a bit more skeptical.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#149

Twenty years ago, I don't think any of us were excited about a future internet where we couldn't trust whether what we were seeing or reading was genuine. I hope one day we'll be able to look back on this era as an aberration, like that scene in Mad Men where the Drapers fling their picnic rubbish onto the grass and drive away.

Are there any examples where it has happened in tech? Maybe internet Pop-ups are closest, that are now automatically blocked. But seems unlikely that we would not use image generation. Just not trust any image by default.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#150
post #147

Twenty years ago, I don't think any of us were excited about a future internet where we couldn't trust whether what we were seeing or reading was genuine. I hope one day we'll be able to look back on this era as an aberration, like that scene in Mad Men where the Drapers fling their picnic rubbish onto the grass and drive away.

I think it may turn out postive; That the less we are able to take images and video at face value the better. Motivated actors have been able to doctor, fake, or spin media content since time immemorial. But peoples default mode was to trust what they saw. Now that fake imagery is ubiquitous, maybe we'll all get a bit more skeptical.

being skeptical and determining the truth takes a lot of work. I fear that we may just refuse to wade through all the lies and just accept a enforced willful ignorance.
Post reply on HN