this post was submitted on 09 Oct 2024
9 points (76.5% liked)

Stable Diffusion

4977 readers
6 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
db0@lemmy.dbzer0.com
Even_Adder@lemmy.dbzer0.com
9
Question about upcoming trends and hardware requirements (lemmy.ml)
submitted 10 months ago* (last edited 10 months ago) by comfy@lemmy.ml to c/stable_diffusion@lemmy.dbzer0.com
12 comments fedilink hide all child comments
 

I want to buy a new GPU mainly for SD. The machine-learning space is moving quickly so I want to avoid buying a brand new card and then a fresh model or tool comes out and puts my card back behind the times. On the other hand, I also want to avoid needlessly spending extra thousands of dollars pretending I can get a 'future-proof' card.

I'm currently interested in SD and training LoRas (etc.). From what I've heard, the general advice is just to go for maximum VRAM.

  • Is there any extra advice I should know about?
  • Is NVIDIA vs. AMD a critical decision for SD performance?

I'm a hobbyist, so a couple of seconds difference in generation or a few extra hours for training isn't going to ruin my day.

Some example prices in my region, to give a sense of scale:

  • 16GB AMD: $350
  • 16GB NV: $450
  • 24GB AMD: $900
  • 24GB NV: $2000

edit: prices are for new, haven't explored pros and cons of used GPUs

you are viewing a single comment's thread
view the rest of the comments
[–] altima_neo@lemmy.zip 7 points 10 months ago* (last edited 10 months ago) (6 children)

Basically, avoid AMD if you're serious about it. Direct ML just can't compete with cuda. Performance with stable diffusion on Nvidia blows away AMD. There's not only performance issues, but often compatibility issues too.

A 4090 is as fast as it gets for consumer hardware. I've got a 3090, and it's got the same amount of vram as a 4090 (24GB), but no where near as fast. So a 3090/TI would be a good budget option.

However, if you're willing to wait, they're saying Nvidia will be announcing the 5000 series in January. I'm not sure when they'll release though. Plus there's the whole stock problems with a new series launch. But the 5090 is rumored to have 32GB vram.

[–] comfy@lemmy.ml 1 points 10 months ago* (last edited 10 months ago) (2 children)

Good to know about CUDA/Direct ML.

I found a couple of 2022 posts recommending 3090s, especially since cryptocoin miners were selling lots of them cheap. Thanks for the heads up about the 5000 release, I suspect it will be above my budget but it will net me better deals on a 4090 :P

[–] WalnutLum@lemmy.ml 4 points 10 months ago

DirectML sucks but ROCm is great, but you need to check if the software you want to use works with ROCM. Also note there's only like 4 cards that work with ROCm as well.

[–] altima_neo@lemmy.zip 2 points 10 months ago* (last edited 10 months ago)

Yeah I don't think 4090 is going down in price. As of now, they're more expensive than when they launched and it seems production is ramping down.

load more comments (3 replies)