80 points
*

No shit that using your PC for any purpose will consume electricity. A modern GPU can generate an image in a couple of seconds. Or I could just play a video game for an hour, and consume a few thousand times more energy

permalink
report
reply
17 points

Yeah, I can’t imagine it’s that different from playing a demanding game. I hear my video card fans spin up harder and sustain that speed for the duration of a play session.

permalink
report
parent
reply
9 points

If you generate images for an hour, it might be about the same as playing a game, depending on how fast you prompt.

But you’re quite right. For most end users it’s entertainment, so this is the proper context.

permalink
report
parent
reply
33 points

Wait so then does playing a game that maxes out my GPU for two hours use enough power to charge 1000 smartphones?

Because that’s a lot.

permalink
report
reply
44 points

A high(er) end smartphone has a battery capacity of approx. 0.019kWh (5000mAh), a gtx3080 has a max power draw of 320W so running that (at max load) for two hours is 0.64kWh, which is equivalent to fully charging ~34 smartphones.

permalink
report
parent
reply
10 points

Thanks for actually doing the math.

permalink
report
parent
reply
5 points
*

So the headline must be false, since you can generate a lot more than 34 generative AI images on a 3080 in 2 hours. That’s if you just include inference though.

I wonder if they are somehow trying to factor in the training costs.

permalink
report
parent
reply
31 points

Bullshit. It has to be way more than that.

As stated above, our study focuses on the inference (i.e. deployment) stage in the model life cycle,

And this is why.

permalink
report
reply
16 points

The model cards for Stable Diffusion 1.5 and 2.1 estimate the CO2 emissions as 11.25 tons and 12 tons for training. XL lacks the info.

A transatlantic flight (round-trip) is about 1 ton per pax. So, while every little bit helps, ML is not where you can make the big gains in lowering emissions.

permalink
report
parent
reply
1 point

If I remember correctly, SDXL is a heavily modified SD2.1, so the numbers might be similar.

permalink
report
parent
reply
24 points
*

While it is good to be cognizant of this, playing AAA games for the same amount of time as the inference (a few seconds ?) is the same as this, right? Since they use the same GPU on consumer hardware.

permalink
report
reply
1 point
Deleted by creator
permalink
report
parent
reply
21 points

Take away all those extra fingers and hands to save energy.

permalink
report
reply
4 points

Top minds are on it.

permalink
report
parent
reply
2 points

I was totally expecting a link to Handi-off (SNL is vigilant about copyright claims on other platforms, sorry for NBC link)

permalink
report
parent
reply

Technology

!technology@lemmy.world

Create post

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


Community stats

  • 17K

    Monthly active users

  • 12K

    Posts

  • 555K

    Comments