> still run on a device like the iPhone, which weights about 170g [1]? The human brain is 8 times heavier.
Why are you comparing the weight? I'm sorry but this is a bizarre comparison. This isn't even apples to oranges, this is apples to a telephone pole.
I'll also throw in that a single Nvidia H100 is 1200 grams. Unless you have a "Bracket with screws" which will add 20 grams (who wouldn't want an extra 20grams of intelligence?).
Like 70%+ of the human brain is water. The human brain needs a massive network of systems to transport nutrients/oxygen which is irrelevant to logical processing.
Similarly the majority of the iphone weight is the battery and frame. The weight of the processing chip is _grams_.
Besides the conflicting variables with the weight, the way that ML works on a physical level is completely different from the human brain.
In their second sentence they have the most honest response I've seen so far at least: " averaged across 4 diverse customer tasks, fine-tunes based on our new model are _slightly_ stronger than GPT-4, as measured by GPT-4 itself."
Does anyone know where I should look if I want to detect specific sounds? Like a smoke alarm, food bowl dispenser (its very distinct), cat meowing, 3d printer collision, that sort of thing?
> Realistically, even with Turbo+LCM, you're still going to 4+ steps (often 8+), with CFG, for reasonable one-generation quality anywhere close to the images people generated at 50+ steps without Turbo/LCM.
For sure the only reason I considered comparing it that way was because the linked repo appears to also be going for a similar approach with 1 step/image on the pi.
From my own experience I've had a hard ever getting a decent image below 6~8steps, but this repo seems more focused on getting it to run in a reasonable amount of time at all, which understandably requires the minimal "maybe passable" settings.
I'm tired of media acting like the flipper is some kind of "super special hacking tool", it is very literally getting it banned in some places when all of it's internals are easy and common radios (Not to knock the flipper, it is conveniently well packaged).
You just needed to be able to send crafted BLE packets, this attack doesn't have anything specific to the flipper at all.
I was just using that as a reference. Stable diffusion will run well with almost any relatively modern gpu.
You don't have to use a 4090, you'll still get double digit performance with a 3060 or whatnot.
> for people who can only otherwise afford Raspberry Pis ;)
You can rent a 4090 for 0.7USD/1hr, or get an A100 for 1.1USD/hr. And if your project is a display + raspberry pi then those costs will dwarf the rental cost.
> I found this claiming an A100 can generate 1 image/s.
The article you linked is over a year old. Needless to say there have been a LOT of optimizations in the last year.
Back then it was common to use 50+ steps for many of the common samplers. Current methods use a few steps like 1. This OnnxStream are using SDXL-turbo, and you can combine LCM and a few other methods to go very fast.
The reason it's so much faster now is the OnnxStream is only using a single step.
However even if you only get 1 image/s with whatever GPU you have I stand by my original statement that unless you want to do it for the cool factor (which is very valid), pre-calculating them makes more sense.
This project is a fun POC but it's not very practical for that type of application.
A 4090 can generate over 100 images a second with turbo+lcm and a few techniques, you can make 2 days worth of images in 1 seconds. You could make a years worth in roughly 3 minutes and put them on the sd card
The most likely "real solution" is going to be using various tricks and finetuning on higher context lengths to just extend the context window. However I will say knowledge graphs are becoming more popular.
I made a comment the other day with a list of some of the popular methods:
Note that there could be something more recent then these that I missed, but as far as I know knowledge-graphs/RAG are what most people are currently using, but there's a lot of work being focused on extending the context window.
> I don’t think it’s a power issue as it’s getting 5V1A from a power outlet directly to USB-C into the device.
It's not the total voltage/wattage the PSU can provide, but the voltage at the processor.
The ESP's varying current draw notoriously causes too much noise and a lot of boards don't have large enough decoupling capacitors so the voltage drops too much and it glitches out. Also a warning that USB PSU's can very MASSIVELY in quality (I'd suggest an apple one for testing if you have one handy).
I think you're right that the RISC-V processor is either better behaved and draws power more consistently, or the board has shorter traces to it's bypass capacitor or a larger bypass capacitor.
> Seeed Studio XIAO ESP32S3/C3, WaveShare ESP32S3 Zero, Unbranded ESP32-WROOM with OLED, Orange Pi Zero W (untouched), Raspberry Pi Zero W (L->R, T->D)
After testing all of these, the only one reliable to work for long periods of time (one month currently) was the XIAO ESP32C3/S3.
I suspect they may be having power issues? For the ESP32's specifically I highly recommend adding a beefy capacitor over the power rails, as those can be rather sensitive to voltage fluctuations especially when transmitting. Both the RPi and ESP's can be finicky depending on the power supply/cable/cable length too, and the RPi's sdcard does tend to fail from sudden power loss. They should all be capable of at least a month, my pi's and esp's have gone several months.
I'd be curious to see the results from other ESP32's (or even the pi) with a larger capacitor added.
Why are you comparing the weight? I'm sorry but this is a bizarre comparison. This isn't even apples to oranges, this is apples to a telephone pole.
I'll also throw in that a single Nvidia H100 is 1200 grams. Unless you have a "Bracket with screws" which will add 20 grams (who wouldn't want an extra 20grams of intelligence?).
Like 70%+ of the human brain is water. The human brain needs a massive network of systems to transport nutrients/oxygen which is irrelevant to logical processing.
Similarly the majority of the iphone weight is the battery and frame. The weight of the processing chip is _grams_.
Besides the conflicting variables with the weight, the way that ML works on a physical level is completely different from the human brain.