News for hackers. Stuff that matters.
Re:Show HN: I stripped DALL·E Mini to its bare essentials an... by etaioinshrdlu on Tuesday June 28, 2022 @02:25AM (#31904725)
Anyone have some stats on inference time and RAM requirements? (on specific hardware)
Re:Show HN: I stripped DALL·E Mini to its bare essentials an... by bart3r on Tuesday June 28, 2022 @03:04AM (#31904979)
I have a 2019 MacBook Pro 2.4Ghz Quad-core i5, 8GB RAM with Intel graphics card

  python3 image_from_text.py --text='a happy giraffe eating the world' --seed=7  154.61s user 22.18s system 262% cpu 1:07.40 total

  WARNING:absl:No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)
As you can see, it took 1min 7seconds to complete.

I assume it would be much faster with a grunty graphics card

Re:Show HN: I stripped DALL·E Mini to its bare essentials an... by chrisa on Tuesday June 28, 2022 @06:11AM (#31905981)
Using an rtx 3090 (NVIDIA gpu with 24GB of RAM):

Mini = 5.33 s

Mega = 14.7 s

Update: about 1/2 that time is just loading the model, so if you load the model and then generate multiple images, it drops to:

Mini = 3.91 s

Mega = 8.86 s