Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stable Diffusion XL 1.0

techcrunch.com

Post reply on HN
Print view View original

31–40 of 182 posts

Re: Stable Diffusion XL 1.0

#31

Post by sdflhasjd »

freediver wrote: post #13

I am completely uninformed in this space. Would someone be kind to explain what the current state of the art in image generation is (how does this compare to Midjourney and others)? How do open source models stack up? Also what are the most common use cases for image generation?

For bland stock photos and other "general-purpose" image generation, DALLE-2/Bing/Adobe etc are... the okayest. SD (with just standard model weights) is particularly weak here because of the small model size.

If you want to get arty, then state of the art for out-of-the-box typing in a prompt and clicking "generate" is probably MidJourney.

But if you're willing to spend some more time playing around with the open-source tooling, community finetunes, model augmentations (LyCORIS, etc), SD is probably going to get you the farthest.

> Also what are the most common use cases for image generation?

By sheer number of image generations? Take a guess...

Re: Stable Diffusion XL 1.0

#32

Post by brucethemoose2 »

jrflowers wrote: post #6

I hope someday there’s a version of this or something comparable to it that can run on <8gb consumer hardware. The main selling point of Stable Diffusion was its ability to run in that environment.

There are several papers on 4/8 bit quantization, and a few implementations for Vulkan/CUDA/ROCm compilation.

TBH the UIs people run for SD 1.5 are pretty unoptimized.

Re: Stable Diffusion XL 1.0

#34

Post by seydor »

Der_Einzige wrote: post #20
tmaly wrote: post #10

I will wait for the automatic1111 web ui version

It's already supported in automatic1111 (see recent updates), and someone in the community will convert it to the automatic1111 format within minutes/hours after it's released on huggingface.

whats the memory usage of sdxl ?

Re: Stable Diffusion XL 1.0

#35

Post by brucethemoose2 »

freediver wrote: post #13

I am completely uninformed in this space. Would someone be kind to explain what the current state of the art in image generation is (how does this compare to Midjourney and others)? How do open source models stack up? Also what are the most common use cases for image generation?

Midjourney may be better for plain prompts, but Stable Diffusion is SOTA because of the tooling and finetuning surrounding it.

Re: Stable Diffusion XL 1.0

#37

Post by PeterStuer »

Let's see wether derived models will suffer less from the 'same face actor'-model response to every portrait prompt. It's not trivial to get photoreal models not lookalike without resorting to specific, typically celeb based, finetunes.

Re: Stable Diffusion XL 1.0

#38

Post by brucethemoose2 »

tmaly wrote: post #10

I will wait for the automatic1111 web ui version

TBH I was hoping the community would take the opportunity to move to the diffusers format...

You get deduplication, easy swapping of stuff like VAEs, faster loading, and less ambiguity about what exactly is inside a monolithic .safetensors file. And this all seems more important since SDXL is so big, and split between two models anyway.

Re: Stable Diffusion XL 1.0

#40

Post by lacker »

I'm out of date on the image-generating side of AI, but I'd like to check things out. What's the best tool for image generation that's available on a website right now? Ie, not a model that I have to run locally.
Post reply on HN