Great idea, where every 10 hours or so it would refresh with a new image it created itself (perhaps based on a theme supplied by the user).

Not very environment-friendly, though.

2.5A 5V is not much power, and it would use considerably less when idling.

125 watt hours for a raspberry pi to generate an image in 10 hours compared to 7 watt hours for a 440W PC to run for 1 minute.

Is this for a regular Pi . The OP post is using a Pi Zero 2.

That is big though

Dude, we are literally using single use plastic bottles to store water for a few weeks in them.

[delayed]

We are literally using LED lighting because it saves energy over conventional light bulbs.

And now we're going to put a screen on the wall that we don't even look at 99% of the time?

If we're doing one bad thing already, we may as well do a hundred!

Compared to what though?

I think it might be friendlier in some aspects than fetching an image from a server running the big the models.

And you don't have to worry about service disruptions or api keys

An e-ink display doing it should only use energy when refreshes. And you could minimize refreshes to once a day, week, etc

Less friendly than a photo of course.

Why do you say that? The energy usage of inference? I would guess that the embodied energy of the digital photo frame is probably higher.

That's where $1999 color E Ink display comes into play.

There are cheaper.. but it might require dithering..

Watch 5 seconds of a tv show with your big tv and you've spent that environmental cost

I'm building exactly that with an eink display atm. Sadly, i can't seem to be able to build the XNNPACK stuff on my pi zero 2W in the repo...

that's an awesome idea, do you have a link to more information?

Ill write it up once it's done and post here, if it gains traction you might see it haha.

In all seriousness I can give a brief overview:

- I'll probably offload the image generation to the 5 year old intel nuc I already have as a home automation server, comfyUI in CPU mode takes 20-30 mins for a generation. Ideally it's all self contained on the Pi but that might be beyond me, skill wise.

- prompts are composed by taking time of day, season, special occasions (birthdays, xmas etc); adding random subjects from a long manually curated list; then asking gpt4 to creatively remix the prompt for variety

- i have an inky impression 7.3 inch 7 color eink display and a raspberry zero stuck onto it. Right now it'll simply download new images from the NUC every once in a while

- i like wood and i dislike the jagged 3d printer aesthetic so I'll create a frame from laser cut plywood by designing some stackable svg shapes in inkscape and sending those to a laser cutter

It works right now, functionally.

Considering that I'm painstakingly writing this on a phone with a sleeping 3 week old baby on my chest it'll be while before i have the energy to make it look like something you'd hang on your wall

Sounds awesome what’s your Twitter ?

I've built this a while back, using a previous version that runs Stable Diffusion on a raspberry pi zero 2 w:

https://hackaday.com/2023/09/19/e-paper-news-feed-illustrate...

https://github.com/rvdveen/epaper-slow-generative-art/