News for hackers. Stuff that matters.
Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by DeathArrow on Wednesday November 29, 2023 @02:21AM (#38456535)
>Open source efforts to produce a similar model seem to have failed due to the extreme compute requirements for finetuning.

A distributed computing project similar to SETI @ Moon wouldn't help with training?

Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by ozr on Wednesday November 29, 2023 @02:45AM (#38456660)
Not really with our current techniques. The increased latency and low bandwidth between nodes makes it absurdly slow.
Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by fivestones on Thursday November 30, 2023 @12:19PM (#38476096)
Do you have any info or links on more details about this? I’ve wondered the same thing.