Train STUNNING LoRAs Locally inside ComfyUI! Low VRAM Flux Tutorial

Поділитися
Вставка

КОМЕНТАРІ • 39

  • @Nishitbeststuner
    @Nishitbeststuner День тому

    If running Runpod, would you rather suggest using this method or the other method using AI-Toolkit in one of your videos?

  • @bartosak
    @bartosak 25 днів тому

    I have just rent a GPU and started looking for this kind of tutorial - THANK YOU!! I love how you slowly explain everything

  • @anseltrust
    @anseltrust Місяць тому +2

    Looks fine, can we train face models on this one like is it working same as the fluxgym?

  • @deyakash2504
    @deyakash2504 Місяць тому

    Hi, small products yes we can get great outputs.. Have you tried training a more complex product? Like a bike or a car? Thanks for sharing your learnings :)

  • @АндрейБогаев-ы2я
    @АндрейБогаев-ы2я Місяць тому +1

    Good Thx. Please tell us about mixing LoRa in one stream (Mix LoRa)

  • @baingeamain5018
    @baingeamain5018 Місяць тому +1

    Does it work for people ? Like I have unfortunately a 8 gb card and I would like to make Lora of people

  • @Beauty.and.FashionPhotographer
    @Beauty.and.FashionPhotographer 24 дні тому

    convert the sample prompts inputs converting to widget does physically not show up nor exist on my version of comfyui, neither does the popup window look the way it looks here. any idea why that is, and if there is a workaround for converting this to a widget? Google does no show any results when searching for this step, ..... see timestamp 8:58

  • @lithium534
    @lithium534 Місяць тому +1

    What video model or service did you use for the last section where they were animated?
    Thanks for the content.

  • @NoFaithNoPain
    @NoFaithNoPain Місяць тому +1

    My question is: If you can have consistant characters, how are consistant outfits achieved? Would it be though a LoRA (so eg you want her in a Space Marine Suit occasionally) wold you make the LoRA and plug it into the consistant AI workflow?

    • @Aiconomist
      @Aiconomist  Місяць тому

      Yes you can use two LoRAs, one for your consistant character, and the other trained for your outfit. Just slightly reduce the strength of the outfit's LoRA.

  • @petera.4707
    @petera.4707 Місяць тому +1

    Thank you! an exceptionally good tutorial with basic information for a noob like me. you are a great teacher!

  • @rmeta3391
    @rmeta3391 Місяць тому +2

    I'll give this a shot. Comfy can do anything! I have both kohya and AI-toolkit installed on my RunPod Network storage. The learning curve for kohya, however, is steep. Thanks for the video. I saw your "handbag" video a few days ago and thought it was pretty professional. You should link that here so others can see it. Sure that Video cost you some major RunwayML credits to get your IG model moving as well as she did. Congraz on that video.

    • @Aiconomist
      @Aiconomist  Місяць тому

      Thanks a lot. It's essentially the same thing. In that video, I used AI-Toolkit instead of this one and Kling instead of RunwayML.

    • @eveekiviblog7361
      @eveekiviblog7361 Місяць тому

      ​@@Aiconomist is ai toolkit process in comfyui?

    • @rmeta3391
      @rmeta3391 Місяць тому +1

      @@Aiconomist Okay, I did see the credits at the end of that video, Kling did a nice job.

    • @Larimuss
      @Larimuss Місяць тому

      Yeh I've been using comfy locally for image gen. It's crazy what it can do. Been trying out lora on runpod. Fluxgym is really quick and easy but it would be good to use comfy then you just have workflows for everything 😂

  • @Musica-qj1nn
    @Musica-qj1nn 19 днів тому

    guy could someone help me plese, why do i have this error: Warning:
    Missing Node Types
    When loading the graph, the following node types were not found:
    VisualizeLoss
    UploadToHuggingFace
    TrainDatasetAdd
    FluxTrainValidate
    FluxTrainValidationSettings
    FluxTrainSave
    OptimizerConfig
    FluxTrainEnd
    FluxTrainLoop
    FluxTrainModelSelect
    TrainDatasetGeneralConfig
    InitFluxLoRATraining
    No selected item
    Nodes that have failed to load will show as red on the graph.

  • @cedricweber4141
    @cedricweber4141 Місяць тому +1

    Can someone tell me if this works on Mac?

  • @Thatlazerlaze
    @Thatlazerlaze Місяць тому

    How did you do the animation at the end?

  • @AmyWarren-u2s
    @AmyWarren-u2s Місяць тому

    Nice work 😊

  • @yasin6904
    @yasin6904 26 днів тому

    "I don't recommend using the portable version" - how come?

  • @ChrissyAiven
    @ChrissyAiven Місяць тому

    Is it crucial that all training pics have the same size? And can they also be like 4:5?

    • @Aiconomist
      @Aiconomist  Місяць тому +1

      Yes it's crucial, the images must be 1024x1024 pixels

    • @ChrissyAiven
      @ChrissyAiven Місяць тому

      @@Aiconomist oh ok...now my training is done and I had like 4:5 ratio but biggest side was 1024px. Well, I do some more testing anyways. My results really need an upscale but they do without the lora too. And I use the same ration and sizes for creation.

  • @ywueeee
    @ywueeee Місяць тому +1

    are you available for custom script work?

    • @Aiconomist
      @Aiconomist  Місяць тому

      Yes, you can find my email in the description box

  • @piyush_kashyap23
    @piyush_kashyap23 Місяць тому

    Can I try this in Google colab free version ?

  • @ronbere
    @ronbere Місяць тому

    i train my loras with it...good but i can't resume

  • @wizhom
    @wizhom Місяць тому

    Can I use Runpod to use this flow?

    • @Aiconomist
      @Aiconomist  Місяць тому

      Yes, you can follow the same steps

  • @guillaumeboucher7769
    @guillaumeboucher7769 Місяць тому

    thanks for the tutorial, the images look really underwhelming. Many features are not matching on the original bag. Its really discouraging to see that type of results.

  • @Anelo96667
    @Anelo96667 Місяць тому

    This is useful contents.
    But I don't think I'd actually use it for a product detail page.
    The products need to match 100% accurately.

    • @SenoSbds
      @SenoSbds 26 днів тому

      Just wait.. It will improving

  • @mneyanmels
    @mneyanmels 23 дні тому

    ValueError, is not a directory ........

  • @guijiao
    @guijiao Місяць тому

    学一下