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

sorenjan | an hour ago

They call it a diffusion model, but it's based on Flux.2 which is a rectified flow model.

MitPitt | an hour ago

Lately I've noticed posts with barely 10 points getting to HN frontpage. Was it always like this?

Aboutplants | an hour ago

I just assume bots

iamjackg | an hour ago

Bots doing what? How would the poster being a bot influence why the post itself makes it to the front page with just 10 points?

speedgoose | 16 minutes ago

It’s about how quickly they get those points. It doesn’t have to be bots. Sending a post to friends with reputable human profiles, and asking for a vote kinda works of most social networks. Some social networks claim they have protection against this but I wouldn’t bet they catch everything.

DannyPage | an hour ago

Not as much competition on the weekend?

s-macke | an hour ago

On weekends, yes. During the week, that’s also true if they arrive within a short time frame, e.g., three minutes. Almost no one looks at “New”. That is the real issue.

robbomacrae | 55 minutes ago

I believe it's the way the HN algorithm works. In order to give new and obscure posts a shot, it will add them to peoples feeds in their front page and see how they measure. Otherwise new posts wouldn't get seen and the flywheel would never get started.

So everyone acts as a sort of beta tester for obscure posts.

nickvec | 10 minutes ago

If you are looking to see the "true" HN frontpage (i.e. most upvoted posts), I'd recommend using https://hckrnews.com

blurbleblurble | 3 minutes ago

Maybe the algorithm has some kind of "momentum" to it, taking into consideration the velocity of upvotes.

yieldcrv | an hour ago

impressive, combines a couple techniques that I always wanted the frontier models to have

having trouble loading the webgl browser demo on my phone but no biggy

lumost | 39 minutes ago

I actually can’t wait for the future where I upgrade hardware in order to upgrade my ai as an alternative to an expensive subscription.

There are many problems I want to work on which require billions of tokens. These are completely inaccessible without corporate project sponsorship at the moment. An asic generation machine which can pump out a few 10s of thousands of tokens per second at opus4.6 quality is more than sufficient.

bigmadshoe | 10 minutes ago

Can you give an example of such a problem?

a1o | 28 minutes ago

Anyone could pickup the minimal hardware requirements for this? Like both RAM and Storage?

SilentM68 | 28 minutes ago

Question,

Is it compatible with Ollama, ComfyUI or are those providers unneeded, compatible with low-end hardware?

Also, where does "./setup.sh/ drop the components in Linux?

Thank you, Sol

wiradikusuma | 26 minutes ago

Is there a benchmark of local image generation models? Local = can run on a 16 GB MacBook or 8 GB+ NVIDIA card.

janniks | 11 minutes ago

I was expecting to see images of Bonsai trees when I clicked this

tobr | 9 minutes ago

I expected a small tree in black and white pixel art.

potatoman22 | 8 minutes ago

I wonder why they didn't use a Bonsai model as the text encoder