Direct pixel-space megapixel image generation with diffusion models
crowsonkb.github.io
Direct pixel-space megapixel image generation with diffusion models
1–10 of 50 posts
Re: Direct pixel-space megapixel image generation with diffusion models
#2I enjoyed this paper (I share a discord with the author so I read it a bit earlier).
It's not entirely clear from the comparison numbers at the end, but I think the big argument here is efficiency for the amount of performance achieved. One can get lower FID numbers, but also with a ton of compute.
I can't really speak technically to it as I've not given it a super in depth look, but this seems like a nice set of motifs for going halfway between a standard attention network and a convnet in terms of compute cost (and maybe performance)?
The large-resolution scaling seems to be a strong suit as a result. :)
Re: Direct pixel-space megapixel image generation with diffusion models
#3I enjoyed this paper (I share a discord with the author so I read it a bit earlier). It's not entirely clear from the comparison numbers at the end, but I think the big argument here is efficiency for the amount of performance achieved. One can get lower FID numbers, but also with a ton of compute. I can't really speak technically to it as I've not given it a super in depth look, but this seems like a nice set of mot…
Thanks a lot!
Yeah, the main motivation was trying to find a way to enable transformers to do high-resolution image synthesis: transformers are known to scale well to extreme, multi-billion parameter scales and typically offer superior coherency & composition in image generation, but current architectures are too expensive to train at scale for high-resolution inputs.
By using a hierarchical architecture and local attention at high-resolution scales (but retaining global attention at low-resolution scales), it becomes viable to apply transformers at these scales. Additionally, this architecture can now directly be trained on megapixel-scale inputs and generate high-quality results without having to progressively grow the resolution over the training or applying other "tricks" typically needed to make models at these resolutions work well.
Re: Direct pixel-space megapixel image generation with diffusion models
#4[flagged]
Re: Direct pixel-space megapixel image generation with diffusion models
#5[flagged]
Making a bank account work for you is a hard discipline and requires budgeting and the like. True, not all of us can "hack" it, but that doesn't mean that with some community classes and help you'll be able to use your bank account well!
Why do I feel like a chatbot with this message.
Re: Direct pixel-space megapixel image generation with diffusion models
#6[flagged]
Making a bank account work for you is a hard discipline and requires budgeting and the like. True, not all of us can "hack" it, but that doesn't mean that with some community classes and help you'll be able to use your bank account well! Why do I feel like a chatbot with this message.
HN to SEO spam pipeline
Re: Direct pixel-space megapixel image generation with diffusion models
#7I enjoyed this paper (I share a discord with the author so I read it a bit earlier). It's not entirely clear from the comparison numbers at the end, but I think the big argument here is efficiency for the amount of performance achieved. One can get lower FID numbers, but also with a ton of compute. I can't really speak technically to it as I've not given it a super in depth look, but this seems like a nice set of mot…
Which discord if its open to the public? I was on one woth kath in 2021 and loved her insights, would love to again
Re: Direct pixel-space megapixel image generation with diffusion models
#8[flagged]
Making a bank account work for you is a hard discipline and requires budgeting and the like. True, not all of us can "hack" it, but that doesn't mean that with some community classes and help you'll be able to use your bank account well! Why do I feel like a chatbot with this message.
You're actually talking to a bot, in this particular case. 12 minutes old with -2 karma. :berk:
Re: Direct pixel-space megapixel image generation with diffusion models
#9Earlier quoted context omitted.
Making a bank account work for you is a hard discipline and requires budgeting and the like. True, not all of us can "hack" it, but that doesn't mean that with some community classes and help you'll be able to use your bank account well! Why do I feel like a chatbot with this message.
You're actually talking to a bot, in this particular case. 12 minutes old with -2 karma. :berk:
Did you seriously just berk me on HN.
What next, is a Walmart cashier going to do that RobloxNite "dab dance" or whatever on me?
Discusting. Dusgraseful.
Re: Direct pixel-space megapixel image generation with diffusion models
#10Earlier quoted context omitted.
Making a bank account work for you is a hard discipline and requires budgeting and the like. True, not all of us can "hack" it, but that doesn't mean that with some community classes and help you'll be able to use your bank account well! Why do I feel like a chatbot with this message.
HN to SEO spam pipeline
Ah yes, the checks notes ever popular bank account hacking SEO spam line.
(Legitimately I am confused but maybe it is a one-two scam or the like, lolz. <3 :')))) ;'PPPP ;'PPPP)