Flux Pulid - Create Consistent Characters From A Single Image - No Lora Needed!

แชร์
ฝัง
  • เผยแพร่เมื่อ 8 พ.ย. 2024

ความคิดเห็น • 55

  • @aitechwitht
    @aitechwitht  หลายเดือนก่อน +5

    0:00 Intro
    0:23 How To Use Flux Pulid Paid (Replicate) And Free (Huggingface)
    1:28 Best And Worst Use Cases - Strengths And Weaknesses Of Pulid
    5:06 Lets Use Flux Pulid - Uploading Our Image
    5:28 Prompting Tips
    6:28 Additional Settings
    8:35 The Generated Images And Additional Tips With More Complex Prompts
    10:23 BONUS TIP - Use Seeds To Create Variations Of An Image
    11:36 BONUS - Pulid Is Perfect For Generating Datasets To Train A Lora
    13:00 Outro

  • @aitechwitht
    @aitechwitht  หลายเดือนก่อน +2

    Flux Pulid allows you to create character consistency from a single image. You can generate images of a character in completely different clothing and lighting scenarios.
    There is no need to use any Loras. In this video I'll highlight both it's strengths and weaknesses.
    It's great to use if you want to generate an entire dataset which you can then later use to train your own Lora to generate images using a free open source solution like Comfy UI or Forge.

  • @ThrowBackZone
    @ThrowBackZone หลายเดือนก่อน +3

    Generating historical figures like Einstein driving a Tesla? That’s the kind of crossover I never knew I needed! 🚗💡

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Sounds like a great idea hahahaha, have fun.

  • @KlausMingo
    @KlausMingo หลายเดือนก่อน +2

    Modern Mona Lisa looks cute :D

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      I think so too hahaha

  • @crippsverse
    @crippsverse หลายเดือนก่อน

    Thank you. Feels like a breakthrough for me 🙂

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      It's actually super awesome! I'm using it to create datasets for training loras.

    • @crippsverse
      @crippsverse หลายเดือนก่อน

      @@aitechwitht This is actually what I've been wanting to create consistent characters for a story I want to animate. It is awesome 🙂

  • @devastaterx
    @devastaterx หลายเดือนก่อน

    Helpful tutorial. Really helped me anyway. 👍👍

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      Thank you so much! I'm glad it helped.

  • @simosemi45
    @simosemi45 หลายเดือนก่อน

    Thanks for this video.

  • @aipoweredmoney
    @aipoweredmoney หลายเดือนก่อน +4

    Could you explore ways to customize the clothing or adding product placement?

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +3

      Currently testing this, however this works better with training a Lora. For instance, I have a character Lora trained on the Mona Lisa so I can generate infinite images of her in Forge for free. Then I trained another Lora on an item of a shoe so the shoe is also consistent when it’s generated . So now in forge I can utilize both loras at the same. I can make the Mona Lisa wear the real shoe item and it remains consistent. Using 2 loras at once can get a bit tricky though. I think we will see a dedicated platform for fashion customisation with consistency, it’s already happening.

    • @homelesspets9234
      @homelesspets9234 หลายเดือนก่อน

      @@aitechwitht would be nice to see you make a video about it when that platform comes up.

    • @lukaszlr6163
      @lukaszlr6163 หลายเดือนก่อน

      @@aitechwitht This may be obvious to many, but what is "Lora"?

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      ​@@lukaszlr6163 A lora is is a way to teach an AI model new tricks without changing its whole brain. It's like adding a small, specialized skill on top of what the AI already knows. So to simplify that, if you use FLUX, it's a big brain pretrained model that generates images. When I train a LORA, I still utilize the big brain but add something new to it to help me extend the big brains capabilities. So instead of FLUX just giving me random images of cats, I can now train a LORA on my own cat and I can teach the big brain how to generate these images of my cat while still utilizing it's full power and potential. Loras allow for customization when generating images, they are extremely useful.

  • @AI_Videos_111
    @AI_Videos_111 หลายเดือนก่อน

    very cool, thanks for sharing!

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Thank you so much bud! I've actually watched a couple of your tutorials and they've been very useful! Keep it up!

  • @googleyoutubechannel8554
    @googleyoutubechannel8554 หลายเดือนก่อน

    You can also just use the lasso tool to cut it out in ms paint if you want the exact same face over and over...

  • @iTrendMedia24
    @iTrendMedia24 หลายเดือนก่อน

    great tutorial !

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Thank you!

  • @Mosen_xd
    @Mosen_xd หลายเดือนก่อน +1

    perfect x2

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Thank you Mosen!

  • @puja1985
    @puja1985 หลายเดือนก่อน

    Referring to the information at the end of the video , I would love to see your workflow for achieving consistent character design in advance live portrait and FOFE, in combination with Pulid, to get different poses. It would be nice if Pulid had some ControlNet features added for pose reference inside replicate it self

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +4

      Thank you Puja! I can certainly put something like this together, basically a deep dive into lora training and how I actually trained the Mona Lisa Lora with the different facial expressions and poses.

  • @AI-EleganceStudio
    @AI-EleganceStudio 5 ชั่วโมงที่ผ่านมา

    How can we change the posture of the face and emotions?

    • @aitechwitht
      @aitechwitht  3 ชั่วโมงที่ผ่านมา +1

      Checkout 12:28, I explain another service that can generate different postures.

  • @ParvathyKapoor
    @ParvathyKapoor หลายเดือนก่อน +3

    not possible for local install?

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      Not that I'm aware of BUT I feel like we will probably get a workflow of this for comfy ui soon or something similar.

    • @DarioToledo
      @DarioToledo หลายเดือนก่อน +1

      yeah an implementation for comfyUI would be delighting.

  • @alaeddinesabbagh7784
    @alaeddinesabbagh7784 หลายเดือนก่อน +1

    can you explain how to use Lora please?

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Planning to release a video on this, won't be focused on humans though as there is many videos on youtube for training loras on your own likeness, i'm going to do something different.

  • @AI-EleganceStudio
    @AI-EleganceStudio 6 ชั่วโมงที่ผ่านมา

    It's a great way to create consistent characters, but it still can't handle facial expressions like sad, angry, or crying faces.

    • @aitechwitht
      @aitechwitht  3 ชั่วโมงที่ผ่านมา +1

      True BUT i've got a great solution for facial expressions, i already recorded a tutorial on how you can generate different expressions, check it out th-cam.com/video/DC3sYgj_byc/w-d-xo.html

    • @AI-EleganceStudio
      @AI-EleganceStudio 2 ชั่วโมงที่ผ่านมา

      @aitechwitht Thank you so much. I just subscribed to your channel today, and that's why I asked about this. 🙂🙏

  • @thehuskyrocky7051
    @thehuskyrocky7051 หลายเดือนก่อน

    how do you create the side view of monalisa?

    • @thehuskyrocky7051
      @thehuskyrocky7051 หลายเดือนก่อน

      like 12:36

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      @@thehuskyrocky7051 it's explained at 12:36 which service is used that generates different poses.

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      @@thehuskyrocky7051 on replicate you need to search for FOFR, their tool is called consistent-character. When you upload an image it will generate different images in different poses while retaining the likeness.

  • @pongtrometer
    @pongtrometer หลายเดือนก่อน

    What about testing a unique object/ product.

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      It unfortunately can't do products or objects, scroll to 4:53. For stuff like this you have to train a Lora.

    • @pongtrometer
      @pongtrometer หลายเดือนก่อน +1

      @@aitechwitht cheers

  • @mr.entezaee
    @mr.entezaee หลายเดือนก่อน

    Does anyone know how to fix this problem?
    Failed to restore node: Ultimate SD Upscale
    Please remove and re-add it.

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      Hmmm, wish I could help but i've never seen this error code, did you manage to figure it out?

    • @mr.entezaee
      @mr.entezaee หลายเดือนก่อน

      @@aitechwitht No, I told me it is because of a knot that must be removed. But I don't know which one and how to find it

  • @henrysingletary
    @henrysingletary 24 วันที่ผ่านมา

    Does it allow you to generate NSFW images?

  • @malusjoon
    @malusjoon หลายเดือนก่อน +3

    With your own photos, it dosn't work. Thats why i want use it.

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +1

      Yup this is unfortunately true however I did mention this in the video when I was discussing best and worst use cases at 4:44 when I tested pictures on myself. For getting good likeness of yourself it’s best to train a Lora for Flux on Replicate or Fal.

  • @TheGoodContent37
    @TheGoodContent37 หลายเดือนก่อน +4

    But how does it fair against Mid journey's cref which does the same?

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน +6

      @@TheGoodContent37 I think it holds up very well in comparison to Midjourney but to be honest, Midjourney cref is better as it can do some slightly varied expressions as well. The biggest plus here is that this offers a service similar to Midjourney for a fraction of the cost or even completely for free on hugging face even though you can only generate a couple images. Once a pulid for flux workflow like this exists for comfy ui, then we can do this with open source tools and generate infinite consistent characters from a single image for free, forever, using our own hardware. For me personally I think that open source is the future of Ai tools.

  • @zGenMedia
    @zGenMedia หลายเดือนก่อน

    why does youtubers say further ado.

    • @aitechwitht
      @aitechwitht  หลายเดือนก่อน

      Hahaha I've always said this on all of my tutorials, it's become more of a habit and a way to say "let's get started".