FLUX REDUX Simplified Workflow

Поделиться
HTML-код
  • Опубликовано: 27 янв 2025

Комментарии • 45

  • @noNumber2Sherlock
    @noNumber2Sherlock Месяц назад +3

    Excellence! What sets you apart from others is how you explain each step, teaching as you inform. You are not just giving "fish", you are teaching "how to fish". Thank you. Subbed!

    • @goshniiAI
      @goshniiAI  Месяц назад +1

      Thank you so much for the encouraging words! It's really rewarding to know you found the walkthrough and explanations helpful. I appreciate your sub!! and Welcome to the channel, family.

    • @noNumber2Sherlock
      @noNumber2Sherlock Месяц назад

      @goshniiAI Truly, you are a class act. Even your tutes to download, your thoughtfulness to provide everything: including images to help along with what you've taught us. I am a little above novice and I learned more from one of your videos over 4 of some others out there. :) Thank you!

  • @vandozz7561
    @vandozz7561 2 месяца назад +4

    Finally, a step-by-step lesson showing the whole process of connecting nodes, thank you very much man 🙏

    • @goshniiAI
      @goshniiAI  2 месяца назад

      I'm glad you found it helpful! You are very welcome. 🙏

  • @patrikvonporat
    @patrikvonporat 15 дней назад

    Thank you, I usually don't comment on videos but this one helped me a lot.

    • @goshniiAI
      @goshniiAI  14 дней назад

      thank you for taking the time. i appreciate your contribution.

  • @discotek1198
    @discotek1198 Месяц назад

    bro, this video tutorial is really good, precise, quick and to the point without all the bullshit most of youtubers do. I really like this style. Subscribed

    • @goshniiAI
      @goshniiAI  Месяц назад

      I appreciate your support and thank you for being here-welcome to the family!

  • @iftekhermorshed2357
    @iftekhermorshed2357 2 месяца назад +1

    Precise details from the scratch which is actually helpful, Thanks a lot!

    • @goshniiAI
      @goshniiAI  2 месяца назад

      You're welcome, and thanks a lot! I appreciate your thoughts on this.

  • @michaellorne5326
    @michaellorne5326 2 месяца назад

    Wow, thank you so much! You may have finally made me a full Comfy convert, something I have resisted so far.

    • @goshniiAI
      @goshniiAI  2 месяца назад

      That is wonderful to hear! I am glad the videos had such a big impact. Welcome to the comfy family.

  • @Jem-ZEE
    @Jem-ZEE Месяц назад +1

    Beautifully define things short and precise tutorial. 👍

    • @goshniiAI
      @goshniiAI  Месяц назад

      Thank you for the kind words and for watching!

    • @Jem-ZEE
      @Jem-ZEE Месяц назад

      @@goshniiAI i want to see a tutorial of movie poster for more then 3 characters, the characters will be taken from real pictures. Its a bit tricky. ComfyUI is a must. 😁
      Thanks

    • @goshniiAI
      @goshniiAI  Месяц назад

      @@Jem-ZEE is definitely a creative and slightly challenging project, but totally doable. lol

  • @JohanAlfort
    @JohanAlfort 2 месяца назад +1

    Awesome, clear and to the point loving your videos man :)
    Does it work to mix this with the depth lora for example?
    Keep it up!

    • @goshniiAI
      @goshniiAI  2 месяца назад

      Yes, even though adding a LoRa will make your style a little more aggressive, it is still possible. To control that, you could use the LoRa strength. Thank you for your uplifting words.

  • @parthwagh3607
    @parthwagh3607 2 месяца назад

    thank you so much.
    How can we apply style of any image to real images, without changing its composition and face

    • @goshniiAI
      @goshniiAI  2 месяца назад

      You are very welcome. I would recommend using ControlNet with Canny guidance to help lock down the composition and facial features.

  • @nickjonas-ze8mm
    @nickjonas-ze8mm Месяц назад

    for your free workflow i subscribed your channel . tnx

    • @goshniiAI
      @goshniiAI  Месяц назад

      Welcome on board, and thank you for your support.

  • @jorgemiranda2613
    @jorgemiranda2613 2 месяца назад

    Really well explained ! Thanks !

    • @goshniiAI
      @goshniiAI  2 месяца назад

      I appreciate your kind words.

  • @kidtoughcamera1
    @kidtoughcamera1 Месяц назад

    I don't know how you figure this stuff out. Some kind of genius. Anyways great video.

    • @goshniiAI
      @goshniiAI  Месяц назад

      Thank you for the high praise. I’m glad you enjoyed the video.

  • @WiLDeveD
    @WiLDeveD 2 месяца назад +1

    very useful tutorial. thanks.

    • @goshniiAI
      @goshniiAI  2 месяца назад +1

      You are very welcome, I'm glad it was helpful.

  • @tonyambito8028
    @tonyambito8028 2 месяца назад

    Nice well explained! Thank you.

    • @goshniiAI
      @goshniiAI  2 месяца назад

      You are welcome. Thank you for sharing your thoughts.

  • @ismgroov4094
    @ismgroov4094 2 месяца назад +1

    good job as always

    • @goshniiAI
      @goshniiAI  2 месяца назад

      I appreciate your feedback. Thank you.

  • @folkeroRGC
    @folkeroRGC 2 месяца назад

    Awesome, but what model of Flux are you using to load in "load Checkpoint", usually I open it in "load diffusion" or "unet loader", thanks we really appreciate it

    • @goshniiAI
      @goshniiAI  2 месяца назад +1

      You are welcome, and you are correct; the process of using your model also works well. I am using the FP8 model saved in the checkpoint point folder, which works similarly to loading an SDXL or SD 1.5 model.
      For clarification, I have described the process in my previous video here ruclips.net/video/TWSFej_S_bY/видео.html

  • @cosymedia2257
    @cosymedia2257 2 месяца назад

    Thank you!

    • @goshniiAI
      @goshniiAI  2 месяца назад

      You are welcome!

  • @watchdog3621
    @watchdog3621 2 месяца назад

    in your model i keep getting a error message StyleModelApply
    Sizes of tensors must match except in dimension 1. Expected size 2048 but got size 4096 for tensor number 1 in the list. how do i fix it

    • @goshniiAI
      @goshniiAI  2 месяца назад

      it could be a resolution issue between the model and the input dimensions. Try resizing the input to (1024x1024) or 2048x2048) to match the tensor size.
      Also running the latest versions of ComfyUI and the StyleModelApply node-updates often resolve compatibility problems.

  • @nikolaprokic2305
    @nikolaprokic2305 Месяц назад

    CLIPVisionLoader
    Error(s) in loading state_dict for CLIPVisionModelProjection: , any help ? updating comfyui doesnt work

    • @goshniiAI
      @goshniiAI  Месяц назад

      Hello there, Confirm that your paths and naming conventions are consistent. Also, make sure the "sigclip_Vision safetensor" is properly installed in your ComfyUI directory.

    • @NikolaProkic-ig2yz
      @NikolaProkic-ig2yz Месяц назад

      ​@@goshniiAI what do you mean by path and naming conventions

  • @Ozstudiosio
    @Ozstudiosio 2 месяца назад +1

    Hi as usually good videos i sent you on other videos i want your contact to speak about business work

    • @goshniiAI
      @goshniiAI  2 месяца назад

      Hello there, Kindly see my previous replies with the details.

    • @Ozstudiosio
      @Ozstudiosio 2 месяца назад

      @@goshniiAI Hi, i dont have any replies from you