Earlier quoted context omitted.
https://github.com/swyxio/ai-notes/blob/main/IMAGE_PROMPTS.m...
#LearningInPublic strikes again! I love you swyx!
haha thank you ser. best way to thank me is to start your own LIP practice and pass it on :)
SDXL Turbo: A Real-Time Text-to-Image Generation Model
141–150 of 157 posts
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#142Earlier quoted context omitted.
I don't try to swim against the current. But you're welcome to do it. What do you mean AI doesn't give back? It serves everyone and gives back everything it can create. Artists are the number one users here, and they will unlock the AI skills better than regular people playing around. What individualized streams? you mean like imagination, where everyone of us has their own "individualized stream"? AI art is augmente…
I think you (and possibly __loam) are talking past one another. You're assuming that artists are just being elitist. While that's not entirely untrue, artistic skill is not merely a gatekeeping exercise. "Just prompt what you're thinking" is great until you need at least a little bit of control over what the AI generates, upon which the whole process disintegrates into banging your head at the model until you get som…
Yes, the vast majority of AI images so far are surprising but not better than human made art, and same for LLM generated text. Maybe they are a new kind of AI slurry, but that's just a phase. If you compare generative art one year ago vs today, or even six months ago vs today you know I am right. It won't be slurry forever. In fact I believe the internet will become an AI feedback system, and much of it will be built with AI.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#143Works with Automatic111. Generated 20 512x512 on a lowly RTS 2070S with 8GB RAM. Prompt: a man Steps: 1, Sampler: Euler a, CFG scale: 1, Seed: -1, Size: 512x512, Model hash: e869ac7d69, Model: sd_xl_turbo_1.0_fp16, Clip skip: 2, RNG: NV, Version: v1.6.0 Examples: https://imgur.com/a/UuuT9qu
I did with Automatic1111 as well. With an RTX 4090 with 24G VRAM, steps 1, cfg scale 1, size 512x512, model sd_xl_turbo_1.0. I was generating more than four images a second.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#144Earlier quoted context omitted.
I think you (and possibly __loam) are talking past one another. You're assuming that artists are just being elitist. While that's not entirely untrue, artistic skill is not merely a gatekeeping exercise. "Just prompt what you're thinking" is great until you need at least a little bit of control over what the AI generates, upon which the whole process disintegrates into banging your head at the model until you get som…
Yes, the vast majority of AI images so far are surprising but not better than human made art, and same for LLM generated text. Maybe they are a new kind of AI slurry, but that's just a phase. If you compare generative art one year ago vs today, or even six months ago vs today you know I am right. It won't be slurry forever. In fact I believe the internet will become an AI feedback system, and much of it will be built…
That sounds completely horrible.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#145Hugging Face released a Colab Notebook for generation from SDXL Turbo using the diffusers library: https://colab.research.google.com/drive/1yRC3Z2bWQOeM4z0FeJ0... Playing around with the generation params a bit, Colab's T4 GPU can batch-generate up to 6 images at a time at roughly the same speed as one.
Is Euler Ancestral recommended for this? I thought the Ancestral samplers added noise to every step, preventing convergence.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#146Earlier quoted context omitted.
>Open source efforts to produce a similar model seem to have failed due to the extreme compute requirements for finetuning. A distributed computing project similar to SETI @ Moon wouldn't help with training?
Not really with our current techniques. The increased latency and low bandwidth between nodes makes it absurdly slow.
Do you have any info or links on more details about this? I’ve wondered the same thing.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#147Hugging Face released a Colab Notebook for generation from SDXL Turbo using the diffusers library: https://colab.research.google.com/drive/1yRC3Z2bWQOeM4z0FeJ0... Playing around with the generation params a bit, Colab's T4 GPU can batch-generate up to 6 images at a time at roughly the same speed as one.
Does Turbo (the model, not this particular notebook) support negative prompts?
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#148Noncommercial 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 posted about my AI porn site pornpen.ai here last year and it reached the top of the front page. And yes, it's still going strong :D (and we've integrated SDXL and videos recently)
oh wow you just got another user sir/madam GYAAAT
Edit: okay a lot of these look just bizarre as hell and seems to favour massive grotesque breast size
I wonder the damage on women this does
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#149Noncommercial 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…
It's not just porn, there is also copyright infringement, fraud, etc.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#150Earlier 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…
>do laws adequately protect people (kids)? Can they? Will this force a shift towards actually chasing producers, distributors, and diddlers? It's extremely complicated. Actual CSAM is very illegal, and for good reason. However, artistic depictions of such are... protected 1st Amendment expression[0]. So there's an argument - and I really hate that I'm even saying this - that AI generated CSAM is not prosecutable, as…
Could this perhaps fall under something like trademark, like an unauthorized use of self, I'm sure I've heard of some celebrity cases that were for similar.