Re:Stable Diffusion with Core ML on Apple Silicon
by behnamoh on Thursday December 01, 2022 @04:53PM
(#33823436)
This may sound naive, but what are some use cases of running SD models locally? If the free/cheap options exist (like running SD on powerful servers), then what's the advantage of this new method?
[ Parent
| on HN ]
Re:Stable Diffusion with Core ML on Apple Silicon
by mensetmanusman on Thursday December 01, 2022 @05:38PM
(#33823985)
Soon you will be able to render home imovies like they were edited by the team that made the dark knight (which costs ~$100k/min if done professionally).
Re:Stable Diffusion with Core ML on Apple Silicon
by m463 on Thursday December 01, 2022 @07:31PM
(#33825171)
"A long time ago in a galaxy far, far away"
but seriously, I wonder when you'll be able to paste in a script, and get out a storyboard or a movie
Re:Stable Diffusion with Core ML on Apple Silicon
by jwitthuhn on Thursday December 01, 2022 @05:35PM
(#33823953)
Even with the slower pytorch implementation my M1 Pro MBP, which tops out at consuming ~100W of power, can generate a decent image in 30 seconds.
I'm not sure exactly what that costs me in terms of power, but it is assuredly less than any of these services charge for a single image generation.
Re:Stable Diffusion with Core ML on Apple Silicon
by sofaygo on Thursday December 01, 2022 @05:02PM
(#33823553)
> There are a number of reasons why on-device deployment of Stable Diffusion in an app is preferable to a server-based approach. First, the privacy of the end user is protected because any data the user provided as input to the model stays on the user's device. Second, after initial download, users don’t require an internet connection to use the model. Finally, locally deploying this model enables developers to reduce or eliminate their server-related costs.
Re:Stable Diffusion with Core ML on Apple Silicon
by huggingmouth on Friday December 02, 2022 @06:38AM
(#33829219)
Stability! The main reason why I use it locally is because I don't want some random dev unilaterally deciding to change or "sunsetting" features I rely on.
Centralized services small and large are guilty of this and I'm sick of it.
Re:Stable Diffusion with Core ML on Apple Silicon
by yazaddaruvala on Thursday December 01, 2022 @05:27PM
(#33823875)
"Hey Siri, draw me a purple duck" and it all happens without an internet connection!
If you mean monetary usecases: Roughly something like Photoshop/Blender/UnrealEngine with ML plugins that are low latency, private, and $0 server hosting costs.
Re:Stable Diffusion with Core ML on Apple Silicon
by gjsman-1000 on Thursday December 01, 2022 @04:58PM
(#33823501)
Powerful servers with GPUs are expensive. Laptops you already own, aren't.
Re:Stable Diffusion with Core ML on Apple Silicon
by tosh on Thursday December 01, 2022 @04:56PM
(#33823473)
Works offline, privacy, independent of SaaS (API stability, longevity, …). I'm sure there are more.
Re:Stable Diffusion with Core ML on Apple Silicon
by alphatozeta on Thursday December 01, 2022 @06:17PM
(#33824435)
fine tuned custom models, models with IP knowledge, models that know what you look like. Better latency etc etc. Obviously some can be served by models hosted locally. You can host a model with Triton and create an API to call it in your native application.