💥No pixel to high quality image for free!-install best upscale model ever in ComfyUi- Solved issues

Поділитися
Вставка
  • Опубліковано 9 лис 2024

КОМЕНТАРІ • 42

  • @Jockerai
    @Jockerai  Місяць тому

    click the link below to stay update with latest tutorial about Ai 👇🏻 :
    www.youtube.com/@Jockerai?sub_confirmation=1

  • @samu7015
    @samu7015 Місяць тому +1

    This is just unbelievable! I took an image of Nicolas Cage where you can barely recognize him, ran it 3 times on the results, and the final output is him in super high resolution. Crazy! I love it, amazing job brother! Thanks for sharing!

    • @Jockerai
      @Jockerai  Місяць тому

      Nice work buddy. Happy to hear you liked this method. It is the best for now

  • @weeliano
    @weeliano 18 днів тому

    Excellent work and many thanks for sharing your workflows!!!

  • @onurerdagli
    @onurerdagli Місяць тому +1

    Thank you! I downloaded and tried many Supir workflows, and this is the only one that works great with amazing quality. Your workflow is very easy to understand and well-organized. I used the RealVisXL V50 SDXL model on my RTX 3060 with 12GB VRAM, and it took 4 minutes. The quality is definitely worth the wait.

    • @AInfectados
      @AInfectados Місяць тому

      How many steps, you tried, with pics where there are medium-small distance faces, i note it changes the original features faces a little.

    • @Jockerai
      @Jockerai  Місяць тому

      Great to hear! 🤩

  • @Gator762
    @Gator762 Місяць тому

    I've tried numerous images, I keep getting error "stack expects a non-empty TensorList". I updated all, and using the same ForRealXL ver .3 and added VAE
    Any ideas on this error?

  • @MJ12GRAVITON
    @MJ12GRAVITON Місяць тому

    Thanks!!!

    • @Jockerai
      @Jockerai  Місяць тому +1

      @@MJ12GRAVITON 🌱🙏🏻

  • @Darkprayers
    @Darkprayers Місяць тому

    Great video's @Jockerai. The 3rd picture featured in the beginning of your video is an old B&W photo that turns to color with the slider. What setting or checkpoint is that found in? Did I miss something in the 2 video's? I tried to have ChatGPT make a description for full color but that didn't work. Keep up the great work sir! Love your video's!

    • @Jockerai
      @Jockerai  Місяць тому

      @@Darkprayers you're welcome bro. The upscaling was with the spuir but colorizing not. For colorizing that image I used an ai website that is especially doing that. I forgot the name of that just searched in google

    • @Darkprayers
      @Darkprayers Місяць тому

      @@Jockerai TY sir! Great work!

    • @Jockerai
      @Jockerai  Місяць тому

      @@Darkprayers you're welcome buddy

  • @CarlosDiaz-t2j
    @CarlosDiaz-t2j 19 днів тому

    SUPIR_conditioner
    module 'tensorflow' has no attribute 'Tensor' error, I have the 4090 and I did follow all the steps

  • @zewez58
    @zewez58 Місяць тому

    Спасибо, все получилось отлично.

  • @TC-1207
    @TC-1207 Місяць тому +1

    Any chance of creating a video on how to get Flux installed and working in Forge UI. Thanks.

    • @AInfectados
      @AInfectados Місяць тому

      You don't need any video really, FLUX works by default with the latest version of FORGE since some time now.

    • @Jockerai
      @Jockerai  Місяць тому +1

      Yes there is I try to do that and make a video

  • @josephrguezglez8670
    @josephrguezglez8670 Місяць тому

    hi, everything is fine but in the middle of the scaling it gives me this error: mixed dtype (CPU): expect parameter to have scalar type of Float

    • @Jockerai
      @Jockerai  Місяць тому

      this could be either because there's not enough precision to represent the picture, or because your video card does not support half type. try setting the "upcast cross attention layer to float32" option in settings > stable diffusion or using the --no-half commandline argument to fix this. use --disable-nan-check commandline argument to disable this check.

  • @davidmanas95
    @davidmanas95 Місяць тому

    Hey master, I have a problem, when upscaling, the final photo is enhanced but there are faces all over the photo, why does this happen?

    • @Jockerai
      @Jockerai  Місяць тому

      @@davidmanas95 make sure to use very proper prompt. What is your prompt that makes such result?

    • @davidmanas95
      @davidmanas95 Місяць тому

      @@Jockerai The prompt is: "A high-resolution photo of a beautiful girl with soft blonde wavy hair, wearing a blue dress. The girl has striking blue eyes, full natural lips, and a calm, confident expression." and when the upscale finish the final image has faces all over the picture, I dont know why

    • @Jockerai
      @Jockerai  Місяць тому

      @@davidmanas95 I have to see your whole workflow can guess what is wrong

  • @FollowViktor
    @FollowViktor Місяць тому

    Thank you for videos. It seems that UltimateSDUpscale isn't working with Comfy anymore. It will no longer install.
    Do you know of this? Perhaps of another place to download a version of it that still works?

    • @Jockerai
      @Jockerai  Місяць тому

      you're welcome bro. No it is still working and last update is for 2024-07-17

  • @alirezafarahmandnejad6613
    @alirezafarahmandnejad6613 Місяць тому

    hi, i get this error in ksmapler:
    RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float

    • @josephrguezglez8670
      @josephrguezglez8670 Місяць тому

      I have the same error, could you fix it?

    • @alirezafarahmandnejad6613
      @alirezafarahmandnejad6613 Місяць тому

      @@josephrguezglez8670 yup, change dtype to bf16 and fp16, anywhere that is on auto in the flow, still i hit another error after this, and after ksampler done, mismatch color error stuff

    • @Jockerai
      @Jockerai  Місяць тому

      this could be either because there's not enough precision to represent the picture, or because your video card does not support half type. try setting the "upcast cross attention layer to float32" option in settings > stable diffusion or using the --no-half commandline argument to fix this. use --disable-nan-check commandline argument to disable this check.

  • @milindtorney576
    @milindtorney576 Місяць тому

    @Jockeri getting this error. Any idea. SUPIR_sample
    Trying to convert Float8_e4m3fn to the MPS backend but it does not have support for that dtype.

    • @Jockerai
      @Jockerai  Місяць тому

      Pls send a screenshot of your wf in telegram

  • @Yuuyu_play
    @Yuuyu_play Місяць тому

    ❤❤❤

    • @Jockerai
      @Jockerai  Місяць тому

      ❤️❤️🤞🏻

  • @AInfectados
    @AInfectados Місяць тому

    👏😎

  • @spacemike800
    @spacemike800 Місяць тому

    updated all, installed missing but get this errors
    --
    Prompt outputs failed validation
    VAELoader:
    - Value not in list: vae_name: 'ae.sft' not in ['ae.safetensors', 'taesd', 'taesdxl', 'taesd3', 'taef1']
    DualCLIPLoader:
    - Value not in list: clip_name2: 't5xxl_fp16.safetensors' not in ['clip_l.safetensors']
    UNETLoader:
    - Value not in list: unet_name: 'flux1-dev.safetensors' not in []

    • @Jockerai
      @Jockerai  Місяць тому

      Make sure you select every model (vae, text encoders...) one by one and have them in proper directory folders

    • @spacemike800
      @spacemike800 Місяць тому

      @@Jockerai Thanks man, that was my problem, fixed now!