NVIDIA SANA In ComfyUI - 100 Times Faster Than Flux And Render 4K Images

แชร์
ฝัง
  • เผยแพร่เมื่อ 15 ธ.ค. 2024

ความคิดเห็น • 163

  • @TheFutureThinker
    @TheFutureThinker  3 วันที่ผ่านมา +9

    I listed all diffusion model, vae link in this blog post, so how YT don't like HF links in description.
    thefuturethinker.org/nvidia-sana-in-comfyui-setup-tutorial-guide/

    • @KaganParlatan
      @KaganParlatan 2 วันที่ผ่านมา +6

      Please provide us working vae link. All people having problem with grey,black,blurry colorful images. Someone told that oldest version working, give it a chance and inform us.

  • @luislozano2896
    @luislozano2896 3 วันที่ผ่านมา +21

    The fastest at making a blank image! RIP ExtraVAELoader.

  • @dhanang
    @dhanang 4 วันที่ผ่านมา +35

    Damn, the pace of AI development right now is just ridiculous. Something I learned 3-6 months ago is already outdated.

    • @bobdole3251
      @bobdole3251 4 วันที่ผ่านมา

      @@dhanangright

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา +3

      @dhanang sometimes wake up another, a new thing release

    • @maknien
      @maknien 3 วันที่ผ่านมา +7

      3-6 Months?? I'd say 3-6 Weeks max 😅

    • @crazyleafdesignweb
      @crazyleafdesignweb 3 วันที่ผ่านมา +3

      ​@@maknien3-6 days😂

    • @Larimuss
      @Larimuss 3 วันที่ผ่านมา +1

      Don’t even bother watching videos from a month ago 😂, honestly every time I open my TH-cam a new major model is out including 2x video models. New apps, new quants, new great workflows, new control nets 😂 I can’t download fast enough

  • @Burnrate
    @Burnrate 3 วันที่ผ่านมา +12

    If you get black you can get the oldest vae from the commit history on hugging face. There is only one vae file in that commit and it works at the moment.

    • @Pernicuz
      @Pernicuz 2 วันที่ผ่านมา +1

      yup that worked for me too, thanks!

    • @kaiserscharrman
      @kaiserscharrman 2 วันที่ผ่านมา +4

      @@Pernicuz I downloaded what I thought would have been the oldest version, but without success, still a black image. could you guys please leave a direct link here ? thanks a lot

    • @glenyoung1809
      @glenyoung1809 2 วันที่ผ่านมา +1

      Thanks for the pointer it worked, this should be the top comment.
      Download the earliest vae model and it works, looks like they broke something in the meantime.

    • @glenyoung1809
      @glenyoung1809 2 วันที่ผ่านมา +1

      @@kaiserscharrman Tried leaving a link but YT immediately deletes the comment.
      The commit number is 38ebe9b227c30cf6b35f2b7871375e9a28c0ccce

    • @gosammy1971
      @gosammy1971 วันที่ผ่านมา

      i don't think that this is the VAE, the Ksampler shows no preview at all and all samples i have seen have ksampler preview. The extra models are simply broken.

  • @alpaykasal2902
    @alpaykasal2902 3 วันที่ผ่านมา +2

    i LOVE that your hobby came through in this video!!!!

    • @TheFutureThinker
      @TheFutureThinker  3 วันที่ผ่านมา

      I am not just tech and AI 😄😅

  • @cr_cryptic
    @cr_cryptic 8 ชั่วโมงที่ผ่านมา

    Great video! Thanks! 🙏

  • @РоманСырватка
    @РоманСырватка 4 วันที่ผ่านมา +16

    I did everything as in the video. I downloaded all the databases. It is generated without errors , but the end result is a black square ((
    ComfyUI has been updated. Does not help. (
    config win 10/10400/64 gb/ 3080 10gb (latest drivers)

    • @dnero6911
      @dnero6911 3 วันที่ผ่านมา +7

      I'm also only getting black images

    • @alexiannelli1010
      @alexiannelli1010 3 วันที่ผ่านมา +6

      Same. I just get grey square.

    • @VuTCNguyenArtist
      @VuTCNguyenArtist 3 วันที่ผ่านมา +2

      I got a black gray image too... not sure what I missed... did exactly as the video

    • @dowhigawoco
      @dowhigawoco 3 วันที่ผ่านมา

      same here

    • @dnero6911
      @dnero6911 3 วันที่ผ่านมา

      At least I don't feel like the only one hahaha

  • @SUP3RMASSIVE
    @SUP3RMASSIVE 3 วันที่ผ่านมา +8

    I'm just getting a pixelated mess. 😥

  • @moviecartoonworld4459
    @moviecartoonworld4459 3 วันที่ผ่านมา +6

    The error "Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)" appears. How can I fix this?
    For your information, I am using an RTX 3080.

    • @graylife_
      @graylife_ 2 วันที่ผ่านมา

      @@moviecartoonworld4459 I get the same error. Couldn't find a solution.

    • @MsDalilou
      @MsDalilou ชั่วโมงที่ผ่านมา

      I was exposed to the same message with the general video card in my device RTX3050 4gb
      How did you solve the problem, please?

  • @UnclePapi_2024
    @UnclePapi_2024 4 วันที่ผ่านมา +3

    Competitive Aquarium Design?!!!😱 I didn't know that was a thing!!!.... Oh... Sana is pretty cool too 😁👍

    • @TheFutureThinker
      @TheFutureThinker  3 วันที่ผ่านมา

      @UnclePapi_2024 search it, IAPLC 😉 you might be addicted to this hobby if you like nature, water, animals, and plants.

  • @derek303
    @derek303 3 วันที่ผ่านมา +12

    i get a lot of Missing VAE keys errors, and only black or grey generation (ex. ['encoder.project_in.weight',......)

    • @joechip4822
      @joechip4822 3 วันที่ผ่านมา +1

      Same here - and look at a thread a bit above from this - many users are getting this missing VAE keys message

    • @parthwagh3607
      @parthwagh3607 3 วันที่ผ่านมา +1

      same

    • @generalawareness101
      @generalawareness101 7 ชั่วโมงที่ผ่านมา

      @@parthwagh3607 A eff ton of errors then the ksampler says AttributeError: module 'xformers.ops.fmha' has no attribute 'BlockDiagonalMask'

  • @jorgemiranda2613
    @jorgemiranda2613 4 วันที่ผ่านมา

    Than you for taking the time to explain it !

  • @marshallodom1388
    @marshallodom1388 3 วันที่ผ่านมา +5

    Censored and sanitized for my protection?

  • @knightride9635
    @knightride9635 4 วันที่ผ่านมา +3

    Without finishing the video, how are the hands and realism in general?

    • @Serj_V
      @Serj_V 2 วันที่ผ่านมา

      just black image

  • @MilesBellas
    @MilesBellas 3 วันที่ผ่านมา +1

    Nerdy Rodent was required to remove his Hunyuan video since he is in the UK and there are EU and UK license issues with that model.
    This is video too ?

  • @cgdtb
    @cgdtb 3 วันที่ผ่านมา +2

    Are generated images allowed for commercial use? From what I read in the license files, they are not permitted.

    • @kaiserscharrman
      @kaiserscharrman 2 วันที่ผ่านมา +1

      NO, the license clearly says "non commercial use only". so I don't even bother with the black rectangle it generates due to an VAE issue any longer...

  • @netandif
    @netandif วันที่ผ่านมา

    I am only getting black or grey images.
    This error keeps appearing in console:
    Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in .

  • @modestasgrazys5547
    @modestasgrazys5547 4 วันที่ผ่านมา +1

    I wonder how inpainting and attention to details works with Sana. As far as I’ve seen in this video, Sana mostly fails to correctly represent objects and ignores generation of small details, like skin texture (woman’s example). But if more high quality FLUX-like results will be introduced, it’ll be amazing to have such a fast model to play with

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา

      Well, its a base model and very small size model. So it happened, some type of image not showing detail.

    • @modestasgrazys5547
      @modestasgrazys5547 4 วันที่ผ่านมา

      @ hopefully the infrastructure to fine-tune Sana and use it with other generation pipelines components will be developed soon:))

  • @insurancecasino5790
    @insurancecasino5790 4 วันที่ผ่านมา +2

    I was literally looking at NVDA for a long lol. This is awesome.

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา +1

      Haha 😂😂

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา +2

      But this model still in early stage. Wait for the fine tune.

    • @insurancecasino5790
      @insurancecasino5790 4 วันที่ผ่านมา

      @@TheFutureThinker This is more exciting than a new car, bro. Cause it's freedom to create. That would include a car design with no limits. I want to make smoke paint. It's possible with AI. Thanks for the vids.

  • @Frank_Art
    @Frank_Art 3 วันที่ผ่านมา +1

    hi, i don't know what hapens, always displays error "No package metadata was found for bitsandbytes" , i installed bitsandbytes and reinstalled torch and cuda and the error stays there

  • @tranthanhdong1992
    @tranthanhdong1992 3 วันที่ผ่านมา

    I got error GemmaLoader Can't use dtype 'torch.float16' with CPU! Set dtype to 'default'. I have set it to default, but i got error "The checkpoint you are trying to load has model type `gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date." Can you help me?

  • @italo9537
    @italo9537 2 วันที่ผ่านมา

    The next step is when some company launch a common AI model. For example ... use resource from sd 1.5 in Pony, SDXL, or other model.

  • @Edacuatica
    @Edacuatica 3 วันที่ผ่านมา

    Thank you. Hopefuly, we will be moving from flux to other models.

  • @robertaopd2182
    @robertaopd2182 3 วันที่ผ่านมา +1

    what about sana vs flux dev? can sana win? any do tests alredy?

  • @nicktumi
    @nicktumi 2 วันที่ผ่านมา

    Is there a way to have an output of various cfg levels? I'd think it makes sense to have an array of the different variants.

  • @dsphotos
    @dsphotos 3 วันที่ผ่านมา

    like others same issue on windows 11: GemmaLoader, No package metadata was found for bitsandbytes

  • @bartosak
    @bartosak 4 วันที่ผ่านมา

    Thank You for this video! :)

  • @DIGIMANN-e2t
    @DIGIMANN-e2t 3 วันที่ผ่านมา +2

    Hello, Im new to all this, and Im getting a bit of an error after following your steps, this is the error and I have no idea how to fix it, Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same, might you have an idea how to fix this and help a newbie out. any help is greatly appreciated... so it seems its telling me my model is running on GPU and data is on CPU, not sure how to make the adjustment to have both the same, any ideas, or is there a GPU work flow for this

  • @animation-nation-1
    @animation-nation-1 9 ชั่วโมงที่ผ่านมา

    Thanks, great ideo. shame these models probably don't have controlnets yet?

  • @marcovth2
    @marcovth2 3 วันที่ผ่านมา

    Is there any news on SANA Lora training?

  • @DodiInkoTariah
    @DodiInkoTariah 3 วันที่ผ่านมา

    Does this work with Mac considering it’s Nvidea?

  • @damarcta
    @damarcta 4 วันที่ผ่านมา

    yeah, thanks for the updates!!

  • @Saoru71
    @Saoru71 วันที่ผ่านมา

    Great video! thank you. I'm getting blank images generated even though everything is set up properly. Any ideas why? Edit: Ijust noticed everyone else has already reported it.. oh! and Nvidia's license is extremely non user-friendly...shame

  • @DrMacabre
    @DrMacabre 2 วันที่ผ่านมา

    How is it with generating text in images ?

  • @brianervin2430
    @brianervin2430 3 วันที่ผ่านมา

    I keep getting this at the ksampler: KSampler 'int' object is not subscriptable

    • @omsterdotcom
      @omsterdotcom 2 วันที่ผ่านมา

      I got the same error when I used the whole number 1 .... 1.1 works, so it must be some scripting error

  • @MilesBellas
    @MilesBellas 3 วันที่ผ่านมา

    Maybe a TensorRT version next ?

  • @Ryuraaan
    @Ryuraaan 4 วันที่ผ่านมา

    what's left is to make them read our thoughts xD Typing cost to much time haha

  • @foreropa
    @foreropa 16 ชั่วโมงที่ผ่านมา

    Nice video, but please, when you do this kind of videos, explain how you do things. I´m searching for a way to search inside ComfyUI and I don´t find anyway to do it, I´m stuck almost at the beginning. Edit: Ok, I found a way and now I don´t get how to do the rest because you don´t explain how to do it, so it´s not a comprehensive tutorial as you call it, it´s a tutorial for people that knows what to do.

  • @kattamaran
    @kattamaran 4 วันที่ผ่านมา

    Nsfw? I might try this for up-res of flux fills

  • @kalakala4803
    @kalakala4803 4 วันที่ผ่านมา

    Haha, i remember our office with a 180cm planted tank 😂 when will you setup a new layout again?

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา

      Maybe coming 2025 I join again the IAPLC 😁🤫. And I need to buy some new stone. Too bad AI cannot generate that. LOL

  • @peacetoall1858
    @peacetoall1858 4 วันที่ผ่านมา

    Can it do hands well? Also I guess loras will come to civitai soon enough.

    • @masterwillian7785
      @masterwillian7785 4 วันที่ผ่านมา +1

      yes, im currently developing loras for human realism, the flux process seems hundreds of times longer than this new one from NVIDIA, im happy.

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา

      ​@@masterwillian7785nice 👍 please keep us update on your Lora for Sana.

    • @peacetoall1858
      @peacetoall1858 4 วันที่ผ่านมา

      @@masterwillian7785 That sounds great. Will watch your video on the lora when you release it.

  • @youtubeccia9276
    @youtubeccia9276 4 วันที่ผ่านมา

    Mindblowing o_O

  • @youtubeccia9276
    @youtubeccia9276 4 วันที่ผ่านมา

    Excellent explained like everytime! ❤

  • @Veselin_Angelov
    @Veselin_Angelov 3 วันที่ผ่านมา +2

    The question every user wants to ask, and no developer wants to answer:
    "Does it do hands?"

  • @schnauzeprincessin
    @schnauzeprincessin 9 ชั่วโมงที่ผ่านมา

    Thanks it works

  • @HanaMinhTran
    @HanaMinhTran 2 วันที่ผ่านมา

    output were grey photos even followed your instructions in install on Window

  • @WiseOwlLearning
    @WiseOwlLearning 3 วันที่ผ่านมา

    Hope it supports lora, controlnet and ipadapter soon

  • @taucalm
    @taucalm 3 วันที่ผ่านมา +1

    As its about 4 times smaller database than flux it pretty much cant be better and as variable. What comes to VRAM they should publish specific checkpoints. Like people, cats, dogs, buildings, landscapes etc.. 4 sure its faster. So is SDXL.
    Better in quality? Nope. More variance? Nope.
    I hate the hype going around everything released just to get clicks.

  • @squoblat
    @squoblat 3 วันที่ผ่านมา

    Do LORAs work with this?

  • @SeanieinLombok
    @SeanieinLombok 4 วันที่ผ่านมา

    brooo waiting on aqua scaping channel now :D

    • @TheFutureThinker
      @TheFutureThinker  3 วันที่ผ่านมา

      I know in your place that have beautiful wood 😁 and good water condition for fish

  • @eltalismandelafe7531
    @eltalismandelafe7531 2 วันที่ผ่านมา +1

    It is wonderful for creating landscapes but for creating humans it is very bad, the worst.

  • @chrisgreenwell3404
    @chrisgreenwell3404 3 วันที่ผ่านมา

    Now just need a controlnet for it

  • @golddiggerprankz
    @golddiggerprankz 4 วันที่ผ่านมา

    CPU wahh🤩

    • @TheFutureThinker
      @TheFutureThinker  4 วันที่ผ่านมา

      @@golddiggerprankz yup yup the text encoder do the same as T5 but very lightweight.

    • @FusionDeveloper
      @FusionDeveloper 3 วันที่ผ่านมา +1

      not for generating the image, only for the prompt.

  • @bordignonjunior
    @bordignonjunior 18 ชั่วโมงที่ผ่านมา

    nice tutorial. but it only generates a solid gray image.

  • @traviswatts1305
    @traviswatts1305 3 วันที่ผ่านมา +2

    Did this work for anyone?

    • @vivekkarumudi
      @vivekkarumudi 3 วันที่ผ่านมา

      i am getting two errors back to back "Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm" , "Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm

    • @ДмитрийКарпич
      @ДмитрийКарпич วันที่ผ่านมา

      After 3 hours of googling and re-installing - yes. But... This model feels like proof of concept, not real thing.

  • @petertremblay3725
    @petertremblay3725 2 วันที่ผ่านมา

    I have try Sana and i prefer by far flux, something is just not right in the lighting and details.

    • @Gaitchs
      @Gaitchs วันที่ผ่านมา

      @@petertremblay3725 same with redux and pulid flux still rules

  • @ian2593
    @ian2593 3 วันที่ผ่านมา

    Followed exactly but get "`.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`."

    • @ian2593
      @ian2593 2 วันที่ผ่านมา

      updated comfyui today and it's fixed but now I get the black screen. Will try to find that old vae.

  • @kd4pba
    @kd4pba 2 วันที่ผ่านมา

    Yea so you lost me at search box when you moved the mouse around.

  • @dowhigawoco
    @dowhigawoco 3 วันที่ผ่านมา +3

    i got only a solid grey colored picture ...

    • @wonder111
      @wonder111 3 วันที่ผ่านมา +1

      Same here. Everything is updated, but no image.

    • @TheFutureThinker
      @TheFutureThinker  3 วันที่ผ่านมา

      Make sure got the right VAE for the model. I can't post the HF links on the description, so how YT don't like it.
      And I list it all in my blog post. thefuturethinker.org/nvidia-sana-in-comfyui-setup-tutorial-guide/

    • @sherifOneWay
      @sherifOneWay 3 วันที่ผ่านมา +1

      getting same result did anyone fix it yet ? btw i had downloaded the same vae from the link same as the model

    • @derek303
      @derek303 3 วันที่ผ่านมา +2

      @@TheFutureThinker seems several are having the same issue. Still happening after verifying VAE

    • @KaganParlatan
      @KaganParlatan 3 วันที่ผ่านมา

      I dont know if it is related but google/gemma-2-2b-it does not have access to install.

  • @Kvision25th
    @Kvision25th 2 วันที่ผ่านมา

    iit works but not sure it bether than sd15 or sdxl :(

  • @lucasfrancelino5141
    @lucasfrancelino5141 4 วันที่ผ่านมา

    Ai Never sleeps, dam!

  • @MiracleMan-ol6gd
    @MiracleMan-ol6gd 3 วันที่ผ่านมา

    The downside with Comfyui is not primarily the cluttered UI, but the difficulty in gauging the settings for an optimal output. Trial and error takes precious time, and there are no standardized and proved settings for the best results. Opinions are like rear ends.

  • @purelife_ai
    @purelife_ai 3 วันที่ผ่านมา

    How about people?

  • @RobertMcDonald_trz
    @RobertMcDonald_trz 3 วันที่ผ่านมา

    6:55

  • @peterr6595
    @peterr6595 3 วันที่ผ่านมา

    But I will let SANA sit for a month while you guys work out the kinks. Too much too fast. BTW 16GB cards will be the minimum for 2025. Buy a new GPU before those orange man tariffs kick in.

  • @大支爺
    @大支爺 3 วันที่ผ่านมา +1

    Censored.

  • @biggreg100
    @biggreg100 2 วันที่ผ่านมา

    I

  • @biggreg100
    @biggreg100 2 วันที่ผ่านมา +2

    All I get is a blnk picture on every run.