I've used this + Groq yesterday to augment (with a chrome extension) the infinite fun game from Neal Agrawal, but generate actual images and not only emojis.<p>This feels like the future, near real time image and LLM generation (using Mixtral from Groq as my prompt writer) and Fal API for read time generation!<p><a href="https://x.com/altryne/status/1760561501096575401?s=20" rel="nofollow">https://x.com/altryne/status/1760561501096575401?s=20</a>
For posterity, SDXL Lightning is open source on Hugging Face with a relatively-permissive license: <a href="https://huggingface.co/ByteDance/SDXL-Lightning" rel="nofollow">https://huggingface.co/ByteDance/SDXL-Lightning</a><p>There are a few other UIs for it, e.g. <a href="https://replicate.com/lucataco/sdxl-lightning-4step">https://replicate.com/lucataco/sdxl-lightning-4step</a>
Great speed!<p>As for the quality, I borrowed the query ([1]) that people used to test Stable Diffusion 3 and other models today: "Photo of a red sphere on top of a blue cube. Behind them is a green triangle, on the right is a dog, on the left is a cat".<p>Here is what I got: <a href="https://imgur.com/a/XrAuqCB" rel="nofollow">https://imgur.com/a/XrAuqCB</a><p>To compare it with Stable Diffusion 3: <a href="https://pbs.twimg.com/media/GG8mm5va4AA_5PJ?format=jpg&name=large" rel="nofollow">https://pbs.twimg.com/media/GG8mm5va4AA_5PJ?format=jpg&name=...</a><p>1. <a href="https://news.ycombinator.com/item?id=39467526">https://news.ycombinator.com/item?id=39467526</a>
_Really_ impressive demo but it'd be oh-so-much-more-impressive if it was smooth, right now ex. deleting a word or adding a space causes 4 inferences in quick session so it feels janky (EDIT: maybe intentional? step by step displayed?)<p>Btw this is from fal.ai, I first heard of them when they posted a Stable Cascade demo the morning it was released.<p>They're *really* good, I *highly* recommend them for any inferencing you're doing outside OpenAI. Been in AI for going on 3 years, and on it 24/7 since last year.<p>Fal is the first service that sweats the details to get it to the point it runs _this_ fast in practice, not just in papers. ex. web socket connection, use short-lived JWTs to avoid having to go through an edge function to sign a request with an API key, etc.
How ... can it be so fast? And what is "blob:<a href="https://blbahblah" rel="nofollow">https://blbahblah</a>" image?<p>By the way the racoon is very prone to get two tails if you change the prompt a little. :)
This is incredible. The reduction in latency has a profound effect in terms of the way I interact with this type of tool. The speed benefit is more than just more image generation. The speed here helps me easily keep the same train of thought moving along as I try different things.
Wow this is super impressive but does somebody know a way to generate consistent characters with stable diffusion?<p>What I mean is if my first prompt is a girl talking to cat and second prompt is girl playing with that cat, I want the girl and cat to be the same in both pictures.<p>Is that possible? If so any links or tutorials will be super helpful to learn.
It's curious what it does with single letters. Seems for me to often settle on a small rather detailed building. The more I repeat the letter (e.g., "111" vs "11111111" the odder the building gets. Which I can see now seems pretty sensitive to the seed.
Absolutely love this. Wish URLs were shareable!<p>`late 90s movie poster, 24 hour clock movie "2: Electric Boogaloo" dan aykroyd1`<p>turned out great
Idea: convert this into a side scrolling game where the background gradually and seamlessly transitions into a rendering of the words we are dealing with as we progress.<p>I am imagining the green lush landscape from early parts of the demo to slowly transform into the dry mountainous landscape from later images while new characters appear in the foreground.
Wow this is fast!<p>The results also look great, but the more I see AI generated images the more I believe it is not going to eat jobs.<p>Almost none of the results are production ready. They all contain strange parts. And maybe more important: the look and feel is always the same.<p>It is amazing this works as fast as it does, but I think AI is still in it's 'hype' stage.
What is the difference between SDXL turbo (released last november) and lightning (released 2 days ago?)? I havent seen any discussion of lightning on here the last few days and hnsearch only shows a few posts with no comments.
Incredibly impressive how fast it is.<p>Very disturbing results are just a second away!<p><a href="https://fastsdxl.ai/share/q5oe57udw953" rel="nofollow">https://fastsdxl.ai/share/q5oe57udw953</a>
Insanely cool :)<p>One bug though: when I increment the seed, it renders two image and it takes a bit of jumping up and down in seed numbers to get to the same image.
wow! this is really fast. this is actually at the speed I want image generation to be at. it makes me want to explore and use the tool. everything else has felt like begrudgingly throwing a prompt and eventually giving up because the iteration cycle is too slow.<p>of course the quality of what is being generated is not competitive with SOTA, but this is going in a really good direction!
I had some fun inputting the American Psycho transcript into this. Made a little video [1]. Insane how fast this is, great work!<p>[1]: <a href="https://x.com/TobiasWhetton/status/1761038697074466868" rel="nofollow">https://x.com/TobiasWhetton/status/1761038697074466868</a>
Looking forward to it once it is refined. It still creates some strange artifacts. Within the HN message, the demo image of the baby raccoon in priest robes, one can count five paws.
This is so quick! The demo being publicly consumable is powerful, though SDXL is not immune to abuse or NSFW (and possibly illegal) generations. I wonder who ends up being held accountable for such generations.
Still issues with limbs when using AI generative artwork...<p><a href="https://fastsdxl.ai/share/0y54bhvalknv" rel="nofollow">https://fastsdxl.ai/share/0y54bhvalknv</a>
Who is gonna tell George Lucas?
<a href="https://fastsdxl.ai/share/o8d16q87qkbt" rel="nofollow">https://fastsdxl.ai/share/o8d16q87qkbt</a>