FLUX with FACE ENHANCER 🔥 - Using ComfyUI locally (With Low VRAM and LORA Support)

Поділитися
Вставка
  • Опубліковано 28 жов 2024

КОМЕНТАРІ • 41

  • @puyobock
    @puyobock 2 місяці тому +6

    This channel is underrated, I hope you get the thousands of subscribers you deserve soon.

  • @FredFraiche
    @FredFraiche 2 місяці тому +1

    Very good workflow. It worked from the start. Good job, and thank you!

  • @MultiSeung
    @MultiSeung 2 місяці тому

    other guides used FLUX with SDXL or SD 1.5 for face detailing, but this guide uses FLUX face detailing with LLM. I tried it out and it's great-no loss in detail at all! Thx!

  • @abaj006
    @abaj006 2 місяці тому

    Brilliant workflow, just tried it and it works great. Thanks for sharing and providing a video that explains things.

  • @michaelknight3745
    @michaelknight3745 2 місяці тому

    Perfect addition to your upscaler, nice work. Your segmentation can be simpler by using layermask tho.

  • @zaloarg
    @zaloarg 2 місяці тому +1

    great video, thank you for sharing !

  • @Nurd_Vybe
    @Nurd_Vybe 16 днів тому

    Love the walkthrough. I was able to follow, but I keep getting a "list.remove(x): x not in list" error when I try to generate. Anyone know what might cause this and how to fix?

  • @SouthbayCreations
    @SouthbayCreations 2 місяці тому

    Thank you for the video. Where did you find the loras for the detailer?

    • @xclbrxtra
      @xclbrxtra  2 місяці тому +1

      CivitAI, you can find all the loras there 💯

    • @SouthbayCreations
      @SouthbayCreations 2 місяці тому

      @@xclbrxtra Thank you but I can't find them 🥲🥲😔😔

  • @0609Bhuwan
    @0609Bhuwan Місяць тому

    So does the original image you started with have to be a Flux generated image ?? If it can be a just a photo then can we use a this worlflow for doing a high res face swap with a LoRA generated face ??

    • @xclbrxtra
      @xclbrxtra  Місяць тому

      Yes technically you can, but you will have to finetune the parameters. Most times there's some texture / lighting difference which will although work but make it feel like somethings off

    • @0609Bhuwan
      @0609Bhuwan Місяць тому

      Really keen to know what you think on my questions ? Can we swap a high res face on a photo from a fine tuned Flux LoRA of another person ?? You mentioned you wanted to use your own LoRA generated face but did not due to poor quality

  • @cinematicfilm6559
    @cinematicfilm6559 12 днів тому

    is it possible i can import my main and image (no ai generation) and swap face ?

  • @mikhailshtanko3866
    @mikhailshtanko3866 2 місяці тому +2

    how I can get the same execution time on every node?

  • @bentontramell
    @bentontramell Місяць тому

    Doesn't Face Detailer do all of the segmentation and fixes in one node?

  • @Rachelcenter1
    @Rachelcenter1 2 місяці тому

    if i want to put a celebrity's face on a marble stone statue, would this workflow get me there? if not, can you recommend one?

    • @xclbrxtra
      @xclbrxtra  2 місяці тому

      Technically it should, if you use some lora trained on statues and another lora of the celebrity. Recently the IPAdapter for flux also released but it doesn't work that well for now, maybe in future they update it.

  • @massibob2004
    @massibob2004 Місяць тому

    Hello
    Do you know why your Loara was bad ? Actually I have very good result with only 12 images. I tried other with 60 of images just for test.

  • @JsiaSusus
    @JsiaSusus 9 днів тому

    is there a way to do this without using as much vram? even on a 24 gb rtx 3090 i run out when using it with flux dev

    • @xclbrxtra
      @xclbrxtra  9 днів тому +1

      Bro try using GGUF files for flux dev, for your usecase Q6 would be best. I have used this workflow on RTX 4060 8gb VRAM

    • @JsiaSusus
      @JsiaSusus 9 днів тому

      @@xclbrxtra thanks so much esp for the quick reply!!

  • @franciscobutte
    @franciscobutte Місяць тому

    Anything similar using Forge?

  • @Djonsing
    @Djonsing 15 днів тому

    Is it possible to make a video of this?

  • @romanioamd5319
    @romanioamd5319 Місяць тому

    I didn't understand how only the face on the photo uploaded improve and which nodes need to be disabled?

    • @xclbrxtra
      @xclbrxtra  Місяць тому +1

      Enable the image 2 image and reduce steps, and keep face switch on

    • @romanioamd5319
      @romanioamd5319 Місяць тому

      @@xclbrxtra In which node (give me the node name in workflow) i need reduce steps? do you mean "face switch on"
      enable Enable Face Enhancer in Fast Groups Muter (rgthree) node? or something else specify the specific nodes of the name where I need to perform the actions. I enable in Fast Groups Muter (rgthree) node image 2 image and upload photo, but it still generates a new photo without processing the face on the uploaded photo.

  • @johnmcaleer6917
    @johnmcaleer6917 Місяць тому

    Very nice work however I'm on an M1 MacBook Pro and cannot get past the Sam2Segmentation node in the Face Enhancer section of the workflow... Getting a 'RuntimeError: Input type (c10::Half) and bias type (float) should be the same' error......
    Any ideas from anyone here on how to fix it , if it's indeed possible ??
    Device is set to MPS instead of Cuda.

    • @Dzyamko1
      @Dzyamko1 16 днів тому

      How did you even start it up? Please share. And also add how it works, how long it takes to generate an image with Lora?❤

    • @skyscope
      @skyscope 15 днів тому +1

      @johnmcaleer691, for your information, I had the same problem, Mac Studio M1. The solution was to change fp16 to fp32 in the SAM2Model Loader.

    • @johnmcaleer6917
      @johnmcaleer6917 2 дні тому +1

      @@skyscope thank you, that fixed it...👍

  • @EmoteNation
    @EmoteNation 2 місяці тому

    Can we use face enhancer for video?

  • @Pawel_Mrozek
    @Pawel_Mrozek 2 місяці тому

    Milion tutorials how to use FLUX it in Comfy UI and very few how to set everything to work in normal UI for ordinary people and none how to use Controlnet or IP Adapters without Comfy UI involved.

    • @xclbrxtra
      @xclbrxtra  2 місяці тому +1

      Controlnet and Ipadapters are not that good in flux till now, they don't give SDXL level results. Apart from that if you install ComfyUI, I already have provided workflows so you just need to input prompts that's it. I just explain the logic so if someone wants to tweak something,they can. You can just drag my workflow and it's ready to use.

  • @wqeerwqeer1375
    @wqeerwqeer1375 2 місяці тому

    does it work with only 32GB ram?

    • @xclbrxtra
      @xclbrxtra  2 місяці тому

      It will work with 16 gb ram too if you have a decent graphic card

  • @thewebstylist
    @thewebstylist 2 місяці тому +2

    As soon as ANYone enters the visual nightmare of comfy UI BYE BYE!!