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

SDXL Turbo: A Real-Time Text-to-Image Generation Model

stability.ai

Post reply on HN
Print view View original

71–80 of 157 posts

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#71

Post by __loam »

kmeisthax wrote: post #45
minimaxir wrote: post #2

The license is non-commercial, but: > For clarity, Derivative Works do not include the output of any Model. https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICE... Doesn't that mean that generated images from it should be fine for commercial?

No, it just means that if they sue you, they're pre-committing to not try and foreclose on your own generated outputs by claiming they're derivatives that they would then own. Of course, this is a water sandwich. If model outputs are derivatives of the model, it'd be difficult to argue that the model itself isn't a derivative of all the training data, most of which isn't licensed. So if anything, this covers Stabilit…

I think the artists get to say whatever they want about this bullshit considering it's entirely dependent on their work to even function. I don't think the AI community gets to call the people who make the models possible at all snobs or anything else. The AI people didn't make shit. They should have some respect for the people that do.

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#72

Post by orbital-decay »

kmeisthax wrote: post #48

Noncommercial use - aside from being one of my licensing pet peeves - seems to indicate that the money is drying up. My guess is that the investors over at Stability are tired of subsidizing the part of the generative AI market that OpenAI refuses to touch[0]. The thing is, I'm not entirely sure there's a paying portion of the market? Yes, I've heard of people paying for ChatGPT because it answers programming questio…

Emad just tweeted about the future monetization of their core models. Seems they want to use the Unity model - the original one, not the recent trick Unity pulled. AKA free to use until you make lots of money with it.

https://x.com/EMostaque/status/1729609312601887109

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#73

Post by __loam »

refulgentis wrote: post #69
__loam wrote: post #65

Earlier quoted context omitted.

Sigh I'm really tired of seeing people assume OpenAI is profitable. We have no idea of they are or not and have some indication that they're incinerating money on chatgpt to the point that they're turning off sign ups because they're out of compute.

I'm not sure that's a useful argument insomuch as A) its unfalsifiable until they IPO (reporting indicates they are very, very profitable) and B) running out of GPUs seems like an odd thing to name as an indicator you're _losing_ money. People are genuinely way, way, way underestimating how intense the GPU shortage is.

I haven't seen any reporting about their costs. I'm sure they're making bonkers numbers in revenue, but that doesn't mean they're profitable if they're losing money on every gpt call. You're saying my claim that they're unprofitable is unfalsifiable. The same is true for claims that they're wildly profitable. We just don't know the financial state of the company because they're not public.

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#74

Post by brucethemoose2 »

godelski wrote: post #63
kmeisthax wrote: post #48

Noncommercial use - aside from being one of my licensing pet peeves - seems to indicate that the money is drying up. My guess is that the investors over at Stability are tired of subsidizing the part of the generative AI market that OpenAI refuses to touch[0]. The thing is, I'm not entirely sure there's a paying portion of the market? Yes, I've heard of people paying for ChatGPT because it answers programming questio…

> Porn. It's always porn. I've been surprised at the explosion of porn. Well, not actually. Automatic1111 made that easy and anyone that CivitAI knows all too well what those models are being used for. I mean when you give teenagers the ability to undress their crushes[0] what do you think is going to happen (do laws adequately protect people (kids)? Can they? Will this force a shift towards actually chasing producer…

SDXL and ControlNet are already optimized, if thats what you mean: https://github.com/chengzeyi/stable-fast

(Note the links to various SD compilers).

But the whole field is moving so fast that people aren't even adopting the compilers and optimized implementations at large.

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#76

Post by senseiV »

__loam wrote: post #71
kmeisthax wrote: post #45

Earlier quoted context omitted.

No, it just means that if they sue you, they're pre-committing to not try and foreclose on your own generated outputs by claiming they're derivatives that they would then own. Of course, this is a water sandwich. If model outputs are derivatives of the model, it'd be difficult to argue that the model itself isn't a derivative of all the training data, most of which isn't licensed. So if anything, this covers Stabilit…

I think the artists get to say whatever they want about this bullshit considering it's entirely dependent on their work to even function. I don't think the AI community gets to call the people who make the models possible at all snobs or anything else. The AI people didn't make shit. They should have some respect for the people that do.

The so called "AI People" built the entire architecture, something people didn't think was possible at the scale and quality a year ago, and the matter of "artists should get whatever they want" because it trained on their works isn't the point. Diffusion Models don't rip parts of pictures together, they happen to be trained to make art out of noise, finding patterns in art. same things happening with LLM's in court with the LLama model and book authors claiming it only makes books.

I still remember that piece of art that was submitted to an art contest and won, only to be announced an SD prompt later

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#78

Post by ilaksh »

fernly wrote: post #50
ilaksh wrote: post #24

Does anyone have any idea of when/if there will be a simple way to get commercial access in one step? Like an API or something? Or if they want to charge for it, then maybe a web check out? It's interesting that they finally decided to try to make something commercially restricted. Do they have a watermark or anything that they can use to track down people who use without a license? Also, is there anything like an op…

about my 8th prompt, it told me I had used up my usage and offered an option to sign up for "pro".

Me too, but I need an API.

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#79

Post by ilaksh »

zaptrem wrote: post #47
ilaksh wrote: post #24

Does anyone have any idea of when/if there will be a simple way to get commercial access in one step? Like an API or something? Or if they want to charge for it, then maybe a web check out? It's interesting that they finally decided to try to make something commercially restricted. Do they have a watermark or anything that they can use to track down people who use without a license? Also, is there anything like an op…

Open version predates this one: https://huggingface.co/blog/lcm_lora

Yes but Turbo is 4 times faster.

Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model

#80

Post by godelski »

brucethemoose2 wrote: post #74
godelski wrote: post #63

Earlier quoted context omitted.

> Porn. It's always porn. I've been surprised at the explosion of porn. Well, not actually. Automatic1111 made that easy and anyone that CivitAI knows all too well what those models are being used for. I mean when you give teenagers the ability to undress their crushes[0] what do you think is going to happen (do laws adequately protect people (kids)? Can they? Will this force a shift towards actually chasing producer…

SDXL and ControlNet are already optimized, if thats what you mean: https://github.com/chengzeyi/stable-fast (Note the links to various SD compilers). But the whole field is moving so fast that people aren't even adopting the compilers and optimized implementations at large.

Not really what I mean. I mean TensorRT is faster than that according to their README. By optimized I'm specifically pointing to Llama cpp because 1) it's in C, 2) using quantized models, 3) there's a hell of a lot of optimizations in there. The thing runs on a raspberry pi! I mean not well but damn. SD is still pushing my 3080Ti for comparison.

But I wasn't thinking diffusion. Models are big and slow. GANs still reign in terms of speed and model sizes. I mean the StyleGAN-T model is 75M params (lightweight) or 1bn (full) (with 123M for text). That paper notes that the 56 images they use in the Fig 2 takes 6 seconds on a 3090 at 512 resolution. I have a 3080Ti and I can tell you that's about how long it takes for me to generate a batch size of 4 with an optimized TensorRT model. That's a big difference, especially considering those are done with interpolations. I mean the GAN vs Diffusion debate is often a little silly as realistically it is more a matter of application. I'll take diffusion in my photoshop but I'll take StyleGAN for my real time video upscaling.

But yes, I do understand how fast the field is moving. You can check my comment history to verify if register isn't sufficient indication.

Post reply on HN