Comment on Stable Diffusion XL Turbo can generate AI images as fast as you can type

ubermeisters@lemmy.world ⁨11⁩ ⁨months⁩ ago

• domi@lemmy.secnd.me ⁨11⁩ ⁨months⁩ ago

  I tried it on a 6900 XT recently and generation time was well under half a second.

  Results are not as good as with SDXL but for the time it needs it’s very impressive.

  source
• Paradox@lemdro.id ⁨11⁩ ⁨months⁩ ago

  The author can’t type very quickly

  source

  • ubermeisters@lemmy.world ⁨11⁩ ⁨months⁩ ago

    A rapid dark-tan mammalian with a bushy red tail propels itself upward off the ground to an elevation above or greater of the below canine, whom has a disposition contrary to prodcutivity.

    source
• barsoap@lemm.ee ⁨11⁩ ⁨months⁩ ago

  I’d guess that the ‘realtime’ is a quote from StabilityAI and of course they’re running that stuff on an A100. A couple of seconds is still interactive rate as generally speaking you want to think about the changes you’re making to your conditioning.

  Haven’t tried yet but if individual steps of XL Turbo take ballpark as much time as LCM steps then… well, it’s four to eight times faster. As quality generally isn’t production-ready we’re generally speaking about rough prompt prototyping, testing out an animation pipeline, such stuff, but that has the caveat that increasing step size often leads to markedly different results (complete change of composition, not just details) so the information you gain from those preview-quality images is limited.

  Oh, “production ready quality”: image quality being roughly en par with 4-step LCM means that it’s nowhere near production grade. For the final render you still want to give the model more steps. OTOH I’ve found that some LCM-based merges do in 30 steps what other models need 80 steps for so improvements are always welcome. But I’m also worried about these distilled models being less flexible, pruning only slightly trodden paths that you actually might want the model to take.

  source
• simple@lemm.ee ⁨11⁩ ⁨months⁩ ago

  Well, it is technically as fast as you can type if you’re running a better GPU. The 3060 is pretty mid-tier at this point.

  source

  • TheGrandNagus@lemmy.world ⁨11⁩ ⁨months⁩ ago

    Low end card tbh.

    I’ll get crucified for saying that because people will interpret that as an attack on their PC or something daft like that.

    It’s Ampere, a GPU architecture from 3.5 years ago. And even then, here’s what the desktop stack was like:

    1. 3090 Ti (GA102)

    2. 3090 (GA102)

    3. 3080 Ti (GA102)

    4. 3080 12GB (GA102)

    5. 3080 (GA102)

    6. 3070 Ti (GA102/GA104)

    7. 3070 (GA104)

    8. 3060 Ti (GA104/GA103)

    9. 3060 (GA106/GA104)

    10. 3050 (GA106/GA107)

    It was almost at the bottom of Nvidia’s stack 3 years ago. It was a low end card then (because, you know, it was at the bottom end of what they were offering). It’s an even more low end card now.

    People are always fooled by Nvidia’s marketing and thinking they’re getting a mid range card when in reality Nvidia’s giving people the scraps and pretending they’re giving you a great deal. People need to demand more from these companies.

    source

    • Blackmist@feddit.uk ⁨11⁩ ⁨months⁩ ago

      The pricing makes it a mid range card, because the budget end is just gone these days.

      source

      • TheGrandNagus@lemmy.world ⁨11⁩ ⁨months⁩ ago

        Nvidia conning people into paying what used to be mid range/high end pricing for a low end card does not make it a low end card.

        The 3060 was always a low end card. Because it was on the low end of the product stack.

        source
    • simple@lemm.ee ⁨11⁩ ⁨months⁩ ago

      I know it’s low-end when compared to the newer generations but if we call a 3060 low-end then what do we call people with older GPUs like a 1070?

      source

      • TheGrandNagus@lemmy.world ⁨11⁩ ⁨months⁩ ago

        Should we not compare the 3060 against its own generation/the current one? To me that makes more sense than including the 1000 series or 900 series or something. How far would we go back? Are all cards sold now high end because they’re faster than a GTX 960? Earlier?

        Personally my cut off was cards still on sale either right now or very recently, say within the past year.

        source
• neurogenesis@lemmy.dbzer0.com ⁨11⁩ ⁨months⁩ ago

  I’m on a 3060 and with 4x upscaling it takes about a second and a half.

  source