Stable Diffusion 3 EXPLAINED + Compared VS Midjourney V6 VS DALL•E 3

แชร์
ฝัง
  • เผยแพร่เมื่อ 11 ม.ค. 2025

ความคิดเห็น • 32

  • @CristianCiupe
    @CristianCiupe 10 หลายเดือนก่อน +8

    I think prompt adherence is very important. You can modify and adapt styles, but getting exactly what you want in complex prompts is a really difficult task at the moment.

  • @piteshbhanushali1140
    @piteshbhanushali1140 10 หลายเดือนก่อน +7

    Sd 3 release date ??

  • @aisamsonreal
    @aisamsonreal  10 หลายเดือนก่อน +3

    How do you think SD3 matches up to MJ and DALLE

    • @p_p
      @p_p 10 หลายเดือนก่อน +7

      SD3 will be opensource, = win.
      I dont need any other informations 😂

    • @xevenau
      @xevenau 10 หลายเดือนก่อน +1

      I love the sound of that@@p_p

  • @TheinterfaceTvSeries
    @TheinterfaceTvSeries 10 หลายเดือนก่อน +8

    I'm never, overtly impressed at AI's ability to capture surreal images as much as I am by its ability to capture real images.

    • @GumOnTheWall
      @GumOnTheWall 8 หลายเดือนก่อน +1

      Definitely hard disagree with something like this as ai is easily able to recreate realistic images because those things already exists it's already in its memory it already knows how to do that whereas interpretive or surrealist images are harder for AI to reproduce because it doesn't actually exist in its memory AI cannot actually create things it's never seen before as much as is able to combine elements of existing memories. Therefore being able to adapt to unforeseen situations or surrealist images is objectively more impressive

    • @TheinterfaceTvSeries
      @TheinterfaceTvSeries 8 หลายเดือนก่อน

      @@GumOnTheWall Can't argue with that. For me, however, I wan't to tell stories and make movies. In doing so, I need imagery of basic things like two people sitting at a table and talking, arguing, walking into a room, running. I have a hard time getting AI to generate a basic "over the shoulder" shot. I've had no problem getting AI to generate surreal imagery. I tends to want to do that more often than naught.

    • @GumOnTheWall
      @GumOnTheWall 8 หลายเดือนก่อน +1

      @@TheinterfaceTvSeries yeah I think that's not an issue with understanding realism that's an issue with understanding language AI is not very good with perspective or points of view but I think stable diffusion 3.0 is supposed to be the best at understanding perspective so I think with SD 3.0 it might be a thing of the past

  • @CrocodileDendi
    @CrocodileDendi 7 หลายเดือนก่อน +1

    Finally, a open source version of stable diffusion that slaps MJ and DALLe. Love it

  • @jopansmark
    @jopansmark 10 หลายเดือนก่อน +4

    It's over for Midjourney

  • @williamweatherspoon4527
    @williamweatherspoon4527 10 หลายเดือนก่อน

    Is it possible to get multiple perspectives of the same image?

  • @MarinaArrudaa
    @MarinaArrudaa 10 หลายเดือนก่อน +1

    Blowing mind video again! Thanks

    • @ramn_
      @ramn_ 10 หลายเดือนก่อน

      blow me this

  • @RaitisPetrovs-nb9kz
    @RaitisPetrovs-nb9kz 10 หลายเดือนก่อน

    I am wondering about the Midjourney setting you were using, RAW and -s 40 should keep closer to the prompt without adding Midjourney style

  • @robertovicol9647
    @robertovicol9647 10 หลายเดือนก่อน

    Can you make a video about Sea Art,how to use all his tools and how to create realistic photos?

  • @inout3394
    @inout3394 10 หลายเดือนก่อน +1

    Please make movie about:
    Stable Cascade and Pinokio.

    • @aisamsonreal
      @aisamsonreal  10 หลายเดือนก่อน +1

      Thanks for the idea, I'll look into them

  • @jeffg4686
    @jeffg4686 8 หลายเดือนก่อน

    They should just charge for their best model - they need a business strategy.
    Most doing SD will do it locally.

  • @midnightstories5695
    @midnightstories5695 10 หลายเดือนก่อน

    But isn't MJ based on stable diffusion anyway ? they didn't pull it out of thin air.

    • @aisamsonreal
      @aisamsonreal  10 หลายเดือนก่อน

      No, MJ is not based on SD. Leonardo is, but not MJ

    • @midnightstories5695
      @midnightstories5695 10 หลายเดือนก่อน

      @@aisamsonrealI'm talking about the original model, it may not have been SD but they didn't make their own base !

  • @josemuanespinto7675
    @josemuanespinto7675 10 หลายเดือนก่อน +1

    Hi I can use SD3?

    • @aisamsonreal
      @aisamsonreal  10 หลายเดือนก่อน +2

      It will be released publicly in the next few weeks

    • @josemuanespinto7675
      @josemuanespinto7675 10 หลายเดือนก่อน +1

      @@aisamsonreal Hi, thank you very much for your attention and answer

  • @content1
    @content1 10 หลายเดือนก่อน +1

    Not keen on talking about models that are not out yet. The images could be handpicked by SD. Out of 100 generations, you will get one with the right spelling, or correct position.

    • @titankronos6517
      @titankronos6517 10 หลายเดือนก่อน

      But still SD 3 will be as good as dalle 3 if not more, and considering it will be an open source model, it will definitely have less restrictions and censorship than dalle 3.

    • @jopansmark
      @jopansmark 10 หลายเดือนก่อน

      Go ahead, make 100 generation and see if anything will be even close to sd3

  • @WhereverJasperGoes
    @WhereverJasperGoes 10 หลายเดือนก่อน

    if you had wanted a plant over his left shoulder instead, you could have taken a frame from your own video...

  • @thomashjalmarson7508
    @thomashjalmarson7508 10 หลายเดือนก่อน +1

    Midjourney did at least give the chameleon breathing nostrils. All the others failed.

    • @mauchoamusic
      @mauchoamusic 10 หลายเดือนก่อน

      V6 creates some unbelievable detailed art

    • @jopansmark
      @jopansmark 10 หลายเดือนก่อน

      Cope