AuraFlow in ComfyUI - A First Look at this Truly Open Source Model!

Поделиться
HTML-код
  • Опубликовано: 16 ноя 2024

Комментарии • 77

  • @Dave-rd6sp
    @Dave-rd6sp 4 месяца назад +25

    For a 0.1 version this model is great. It's still not fully trained and it's already better than SD3 in many regards while being truly open source.

    • @taucalm
      @taucalm 4 месяца назад +1

      Using 24gb of VRAM it doesnt seem to be even a good model, but we see in the few passing months.

    • @ilplopperz
      @ilplopperz 4 месяца назад

      @@taucalm ahaha 24gb

  • @juanjesusligero391
    @juanjesusligero391 4 месяца назад +15

    Oh, Nerdy Rodent, he really makes my day; showing us AI, in a really British way.

  • @chaotichuman5120
    @chaotichuman5120 4 месяца назад +7

    I can actually confirm it even runs with 6GB VRAM but only very slowly. "Very slowly" as in "It takes 10 minutes or more to generate a single 1024x1024 image".

    • @NerdyRodent
      @NerdyRodent  4 месяца назад

      Mmm… speedy 😊 Thanks for letting me know!

    • @Ratinod
      @Ratinod 4 месяца назад +1

      Turn off "CUDA System Memory Fallback" and get "CUDA out of memory error". If "CUDA System Memory Fallback" is enabled, then very slow RAM is used instead of fast VRAM. (can be seen in task manager)

  • @DoorknobHead
    @DoorknobHead 4 месяца назад +24

    "Can it do hands?"
    "Can it do muddy red Wellies?"
    Yes. Yes, it can. Welp, passed all my highest priority tests.

    • @NerdyRodent
      @NerdyRodent  4 месяца назад +1

      The essentials!

    • @taucalm
      @taucalm 4 месяца назад +1

      No it cant. Even women dont have six fingers or four hands.

  • @richgates
    @richgates 4 месяца назад +14

    For what it's worth, It runs fine on my 4090 mobile with 16GB of VRAM, albeit a bit slow. I was even able to do a batch size of 4 at 832x1216.

    • @NerdyRodent
      @NerdyRodent  4 месяца назад +1

      Nice!

    • @PhotoBomber
      @PhotoBomber 4 месяца назад

      yup works for me too, but cant do big t*tty goth nsfw

    • @RhysAndSuns
      @RhysAndSuns 4 месяца назад

      looks like its using about 14gb for me doing 832x1152 at about 2.6s/it. Batch of 4 runs, using 15/16gb vram

  • @MrMsschwing
    @MrMsschwing 4 месяца назад +15

    It seems to be at least better than the bare sd1.5 model - and look what the community has made out of that. So a few tweeks and finetunes down the line and we have an interesting sd competetor. Keep us updated!

    • @DanielDota
      @DanielDota 4 месяца назад +1

      I was able to run sd1.5 with 4gb vram though

    • @MrMsschwing
      @MrMsschwing 4 месяца назад

      @@DanielDota I'm sure that number will go down over time

    • @cmh_
      @cmh_ 4 месяца назад

      Unfortunately the community being composed mainly of this rare breed of entitled high end rig gamers and whiny big booba weebs connoisseur they started shitting on the model already and speculating about why they can't achieve their lewd. I wish cool luck to Simo, I'd understand if it's first model is also his last.

  • @pon1
    @pon1 4 месяца назад +4

    Always good for different actors on the scene! A bit of competition is always nice, and it's only in beta so I guess that we will see more from them!

  • @vi6ddarkking
    @vi6ddarkking 4 месяца назад +4

    Not A Bad First Impression.
    Hopefully is good enough for the community to update their tools for it.
    A competitor to SD3 is rather needed right now.

  • @sammcj2000
    @sammcj2000 4 месяца назад +1

    Shows a lot of promise for an early beta, hope to see this come to InvokeAI soon!

  • @buttersstotch6389
    @buttersstotch6389 4 месяца назад +2

    Comfy still looks way more complicated to me compared to A1111 so I haven't taken the plunge yet, but it still interesting to see new things via Comfy.
    PS Nerdy, I like your short theme music at the end. Reminds me of early Stranglers. Would be appropriate if you actually have Rattus Norvegicus in your LP collection.🐀

  • @knoopx
    @knoopx 4 месяца назад +5

    tbh this looks like next big thing to me, cloneofsimo brought us LoRAs and this model can only get better given its license.

  • @balanse01
    @balanse01 4 месяца назад +2

    It's a nice showcase of what seems to be their early access version of the final model, right now it's pretty slow with the uni_pc (1.4s/it with a 3090 on a 1024x1024 image) and produces nice results but nothing ground breaking.
    We also got like no guidance on how to efficiently use this thing and what different cfg and Schulders we can use, I'm very hopeful about the future of this model compared to what stability ai has been making! :)

    • @balanse01
      @balanse01 4 месяца назад

      Also as far as i can tell this thing hasn't been trained on anything that is considered nsfw prompting "naked woman" produces a woman's face with a bunch of hands on the sides and poses are also mixed up so this thing may be "open source" but it's not trying to break the norms and make a uncensored model.

  • @swannschilling474
    @swannschilling474 4 месяца назад +1

    Always a good catch Nerdy!! 😊

  • @pn4960
    @pn4960 4 месяца назад +3

    It looks very promising. Unfortunately the 24 GB requirement is going to be a hard limit to how much it is used by the community.

    • @seto007
      @seto007 4 месяца назад +1

      Mixed reports on this. Some people in the replies have said they can run it just fine on 16GB and 12GB of VRAM.
      It's also hard to gauge just how much VRAM it's using if you're testing it with a batch size higher than 1.

    • @ickorling7328
      @ickorling7328 4 месяца назад

      @@pn4960 if it runs in AMD on RDNA 3, then an igpu can practically ignore vram requirements since igpus use system ram as VRAM on windows. RDNA 3 has an NPU onboard.

    • @Sebucan7
      @Sebucan7 4 месяца назад +1

      I am using a RTX 3060 with 12GB VRAM and all works fine, only a little slow : 2 mins for an image.

  • @Sebucan7
    @Sebucan7 4 месяца назад +2

    I am using a RTX 3060 with 12GB VRAM and it works fine, only a little slow: about 2 mins and 10 secs for an image in average.

  • @silvermushroom-gamifyevery6430
    @silvermushroom-gamifyevery6430 4 месяца назад

    It obviously needs work, and ecosystem stables like controlnet, but open source providing a escape route away from SD’s enshittification is a massive W.

  • @koray1621
    @koray1621 4 месяца назад +7

    Me and my 4 gb of vram crying rn

    • @abaj006
      @abaj006 4 месяца назад +4

      Thats ok, you just need to download another 20gb of VRAM and you will be all set!

    • @jaywv1981
      @jaywv1981 4 месяца назад

      @@abaj006 You can also just plug some VRAM into an available USB port :D

  • @Cyberdjay
    @Cyberdjay 4 месяца назад +1

    I am using a RTX 4070ti with 16GB VRAM and it works great. about 33 secs each image

  • @amortalbeing
    @amortalbeing 4 месяца назад +1

    thanks this was indeed very interesting 🙂

  • @MyAmazingUsername
    @MyAmazingUsername 4 месяца назад +1

    I have a feeling it doesn't have training data with labeled styles at all. Most likely bulk labeled data via neural vision.

  • @fdimb
    @fdimb 3 месяца назад

    Amazing content as always! I'm hoping for some new model or flow that would allow the automation of 3d or 2d models game and animation assets

  • @VaibhavShewale
    @VaibhavShewale 4 месяца назад +1

    what different does this model do? and how much iteration less it takes to crete something good?

  • @ryshabh11
    @ryshabh11 4 месяца назад +1

    Thanks

  • @AIKnowledge2Go
    @AIKnowledge2Go 4 месяца назад

    Thanks for this video. You lost me at 24 GB VRAM... 😂 One of the biggest mistakes I made building my current PC was going for an NVIDIA 4080 with "only" 16 GB VRAM. If I had known what was in store for me, I would have decided to sell a kidney and buy a 4090 instead.

    • @WatchNoah
      @WatchNoah 4 месяца назад

      It runs with 16gb too. Also you can get a cheap used p40 (~300$) with 24gigs of vram as an additional card if you want

    • @fixelheimer3726
      @fixelheimer3726 4 месяца назад

      Save the kidney and get a used 3090

  • @obscuremusictabs5927
    @obscuremusictabs5927 3 месяца назад

    It works in Automatic1111 but won't do text properly. It does text but it's gibberish. Has anyone solved this issue? If I run it in Comfy it is very slow. Like maybe one image an hour. Even running SDXL models in Comfy is painfully slow. I'm using a mac M1. Maybe there's already a solution for this but I'm not aware of one.

  • @Satscape
    @Satscape 4 месяца назад +1

    Oh dear, lost me at the VRAM requirements. 4GB not gonna cut it eh.

  • @trilogen
    @trilogen 3 месяца назад

    Can i run this on my laptop? RTX 3050 Ti

  • @Deadgray
    @Deadgray 4 месяца назад

    I tried it yesterday, limbs quality is like SD3. Lets wait 1 more year.

  • @KC_79
    @KC_79 4 месяца назад +2

    24G of VRAM. Ok, not really related to me then.

  • @MilesBellas
    @MilesBellas 4 месяца назад

    How about "Vchitect Latte"?

  • @PZMaTTy
    @PZMaTTy 4 месяца назад

    My 6gb notebook doesn't like this, but it's actually pretty cool people can run it locally for free

  • @brootalbap
    @brootalbap 4 месяца назад

    24gb??

  • @Radarhacke
    @Radarhacke 4 месяца назад +1

    24GB VRAM? For what? The most community trained SD 1.5 Models do a better job. But thanks for the nice video.

  • @LouisGedo
    @LouisGedo 4 месяца назад +1

    👋

  • @cariyaputta
    @cariyaputta 4 месяца назад

    Is this model contain censorship in any capacity?

  • @sirmeon1231
    @sirmeon1231 4 месяца назад

    Woman on a grass - you got what you wanted!! 😂

  • @NotThatOlivia
    @NotThatOlivia 4 месяца назад

    not usable for now ...

  • @drawmaster77
    @drawmaster77 4 месяца назад +3

    Can't wait to spend $10k on a graphics card so I can generate woman with 4 hands 🙄

  • @makesnosense6304
    @makesnosense6304 3 месяца назад

    "Truly open source" isn't needed if people stopped abusing "open source" on models that should be "open weight".

  • @polymath_wtf
    @polymath_wtf 4 месяца назад

    fixed seed bro

  • @madseraphim
    @madseraphim 4 месяца назад

    you lost me in the 24gb vram

  • @KlimovArtem1
    @KlimovArtem1 4 месяца назад +3

    Almost a year passed since Dalle3 release, and all these open sourced models still cannot achieve its level, sadly.

    • @southcoastinventors6583
      @southcoastinventors6583 4 месяца назад +2

      It more like it depends on the composition because Dalle3 still is bad at people compared to Open Source but it is better at more complicated prompts and can do decent text but at the same time Ideogram does better text and logos so right now there is not a good everything model.

    • @KlimovArtem1
      @KlimovArtem1 4 месяца назад +2

      @@southcoastinventors6583no, not really. Try to make a scene with several humans hugging, or shaking hands. Most open sourced models, including this new one, will mess everything up. Dalle3 performs very well. It’s only weakness - bad photorealism (probably on purpose) and heavy censorship.

    • @southcoastinventors6583
      @southcoastinventors6583 4 месяца назад

      @@KlimovArtem1 Control net and depth maps can easily do those. The point is Dalle3 is bad at things compared to other models and is not as good as ideogram on text and logos.

    • @seto007
      @seto007 4 месяца назад +1

      This is more an issue with text encoders. T5 models tend to perform similarly to Dalle 3 because they process prompts similarly. CLIP is more of a tokenizer than a text encoder. It's mostly just a waiting game now for community adoption of these sorts of models.

  • @UltimatePerfection
    @UltimatePerfection 4 месяца назад

    Can it do NSFW?

  • @PrincessSleepyTV
    @PrincessSleepyTV 4 месяца назад

    lul beata

  • @KINGLIFERISM
    @KINGLIFERISM 4 месяца назад

    Hard pass for now.