31–40 of 157 posts
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
SDXL is already very very slow when compared to SD 1.5. They are claiming 200ms for 512x512 image in SDXL on A100. We need SD 1.5 turbo for even faster generation.
I haven't found SDXL to be inherently much slower than 1.5, besides the obvious 4x slowdown from having twice the linear resolution.
Earlier quoted context omitted.
Are you serious? I'm using Stability in production: they kept their SDXL beta model which was capable of SDXL 1.0 level prompt adherence at a fraction of the cost up for months after was reasonable for a one-off undocumented beta, and it was a huge boon to my product. Then a few weeks back they went and quietly cut costs to 1/5th or so what they were for SDXL and released a model that produced similar quality outputs…
Sounds like they’re doing the same thing OpenAI is doing. Claiming to favor open models but the reality is they’re pumping growth by reducing costs and this lowering prices. They want a massive chunk of this new market, all of it if they can get it. Their perceived valuation then becomes a matter of how many eyeballs they have looking at segments of their website to advertise to, or how many data points they can coll…
There couldn't be a more perfect rebuttal to this theory than the post you decided to leave it under.
Earlier quoted context omitted.
They have a web demo here: https://clipdrop.co/stable-diffusion-turbo
...which requires you to sign in. That nice little text box invites you until you actually click to enter some text and get a registration box thrust at you People that design a UX where the user tricked into a registration 'ambush' need to be punched in the face.
your last four words: nope, hard no, no, we are not friends
Earlier quoted context omitted.
Sounds like they’re doing the same thing OpenAI is doing. Claiming to favor open models but the reality is they’re pumping growth by reducing costs and this lowering prices. They want a massive chunk of this new market, all of it if they can get it. Their perceived valuation then becomes a matter of how many eyeballs they have looking at segments of their website to advertise to, or how many data points they can coll…
This would be a lot more pithy if it weren't in the comment section of a post that showcases exactly how they were likely able to make 1.6 cheaper, and open sources the underlying tech. There couldn't be a more perfect rebuttal to this theory than the post you decided to leave it under.
At what point did I indicate they weren't making it cheaper? Also their licensing isn't really in the spirit of what open source originally described, which is what I meant.
Sorry if that didn't come across, I guess. I was being intentionally pithy but largely related to standard practices for VC funded startups.
Works 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
SDXL is already very very slow when compared to SD 1.5. They are claiming 200ms for 512x512 image in SDXL on A100. We need SD 1.5 turbo for even faster generation.
Earlier quoted context omitted.
I tested a bit and the quality for photorealistic images is surprisingly bad, and definitely worse than LCM and of course normal SDXL. For more artistic images, SDXL Turbo fares better. Unlike normal SDXL, you're required here to use the old-fashioned syntatic sugar like "8k hd" and "hyperrealistic" to align things.
Are there any good resources for learning a lot of "syntactic sugar" terms? This is new to me, but I'd love to know more.
Works 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 just want to point out that I’ve noticed sdxl isn’t good at producing images that are 512x512 for some reason. It works much better with at least 768x768 resolution.