What Makes FLUX Shuttle 3 So AMAZING?

Поділитися
Вставка
  • Опубліковано 29 лис 2024

КОМЕНТАРІ • 69

  • @KDawg5000
    @KDawg5000 15 днів тому +10

    Downloading now to give it a try. One my first tests will be with crowd faces, or basically faces at a distance. The Schnell models always looked bad/distorted vs the Dev, so we will see how Shuttle does.
    UPDATE: After trying it in Forge, it uses so much memory that I can only do 1 image at a time w/my 4090. It has a lot of background blur, so I used the amateur image lora to get a more realistic image. That did improve the results, but still not 100% to my liking. Also it didn't like favorite sampler setup of DEIS and DDIM. Note if you look in the command window you can see this message "Distilled CFG Scale will be ignored for Schnell". So adjusting that really won't make a difference if I understand correctly. Now to test in ComfyUI to see if it works better.

  • @robinmountford5322
    @robinmountford5322 4 дні тому

    Thanks very much for your videos. I feel the schnell model has less of an AI look. Especially the I Love You example where it looks more photo like. Slightly faded text on the card and more natural skin tone.

  • @JustFor-dq5wc
    @JustFor-dq5wc 14 днів тому +4

    Models are from 6.8 GB to 24 GB. It works great on my RTX3060 12GB. Thanks for tip!

  • @adrewbateman1760
    @adrewbateman1760 15 днів тому +3

    Thanks for making these vids !

  • @TR-707
    @TR-707 14 днів тому +1

    Thank you for the headsup.
    One thing I miss and maybe we can cover is - asymetric tiling. I guess FLUX and SD3 totally cant do it like SDXL is able to...

  • @jcvijr
    @jcvijr 14 днів тому

    Examples are impressive, will try it out!

  • @therookiesplaybook
    @therookiesplaybook 9 днів тому

    You don't need the second step thing. You can right click an image in the preview chooser to save the image, but connect the SD ultimate to the image output of the preview chooser to continue the processing if you want.

  • @wasifangel
    @wasifangel 4 дні тому

    How to solve "Tuple index out of range" in comfyui?

  • @valerymoyseenko
    @valerymoyseenko 14 днів тому

    Works fine on 8 VRAM / 32 RAM in Comfyui with Loras and gives very interesting results.

  • @hustlecoin
    @hustlecoin 12 днів тому

    Is this for commercial use? Can't find info on the huggingface page or their website or docs?

  • @JustFor-dq5wc
    @JustFor-dq5wc 14 днів тому +4

    Forge. Model: shuttle-3-diffusion-Q4_K_S.gguf. Memory A: 7.68 GB, R: 8.53 GB, Sys: 9.7/12 GB (80.6%) on GPU 3060 12 GB

  • @murphylanga
    @murphylanga 15 днів тому

    Thank you for your information, it makes me curious what you can do with it 🤓

  • @rapalma38
    @rapalma38 15 днів тому

    Amazing, thanks for sharing your knowledge.

  • @Zenda_Nior
    @Zenda_Nior 15 днів тому +7

    50GB model sets to get 4 step renders, requiring beefy hardware. How is this progress?

    • @JustFor-dq5wc
      @JustFor-dq5wc 14 днів тому

      There is no 50 GB model.

    • @Zenda_Nior
      @Zenda_Nior 14 днів тому

      @@JustFor-dq5wc I did say sets, didnt I?
      Model + Diffuser + Encoder
      Yes 50 is a bit exaggerated but not for long.

    • @JustFor-dq5wc
      @JustFor-dq5wc 14 днів тому +1

      @@Zenda_Nior I know. I kind of mad too. But ... higher hardware requirements are a natural consequence of technological progress. Models are getting more complex. You can have deviation from that, like something highly optimized, but ...

    • @fr0zen1isshadowbanned99
      @fr0zen1isshadowbanned99 13 днів тому

      @@Zenda_Nior After some more testing Yesterday, I sadly have to tell you that you are right with the 50GB.
      It ran pretty slow for 4 Steps and then I tried the .gguf some other Commenter suggested. That failed and just ate all normal 64GB RAM before crashing.
      So back to the normal Shuttle. I still had the Task Manager open and so I took a look at the Shuttle RAM usage... yea... 50 - 64GB usage depending on if you generate or idle.
      It seems that it just so fits into a 24GB VRAM and 64GB RAM System :D I even downgraded the t5xxl_fp16 to the t5xxl_fp8_e4m3fn before checking ^^ But still great Pics! :)

    • @Wyn3e
      @Wyn3e 10 днів тому

      @@fr0zen1isshadowbanned99interesting as mfs ran it fine on 12gb 3060 with 32gb of vram

  • @baheth3elmy16
    @baheth3elmy16 14 днів тому +4

    Thanks for the video! Though you hid most of the nodes links by excessively zooming in. You don't understand that in many countries, Patreon is banned, and we cannot pay you to download the complete workflow. Though, the first group worked and the photo realistic images are terribly plastic.

  • @ysy69
    @ysy69 15 днів тому

    Thanks Olivio! Do you know if all flux LoRas work with this model?

  • @microfino
    @microfino 14 днів тому

    Love the shirt Olivio!

    • @OlivioSarikas
      @OlivioSarikas  14 днів тому

      Thank you, you can actually get it here and even get a $1 discount by using Olivio as a discount code :) www.qwertee.com/shop/tees/grumpycorn

  • @Elwaves2925
    @Elwaves2925 15 днів тому

    Cheers Olivio. I'll give this a go but as it's trained off Flux Schnell, I can see me sticking with RealFlux and Pixelwave. Still, it's nice for those who want something quicker.

  • @feflechi
    @feflechi 12 днів тому

    I wish we had seen more examples

  • @AI_ART_MASTER
    @AI_ART_MASTER 15 днів тому

    hey Olivio what hardware/desktop do you recommend to use FLUX with that generates fast?

  • @michaelbayes802
    @michaelbayes802 15 днів тому

    Hi, thanks Olivio for the video. I saw the size of the file is nearly 24 GB. I guess that means with a 16 GB VRAM running it will not be possible.

    • @OlivioSarikas
      @OlivioSarikas  14 днів тому

      i have 16GB and it run fine. Someone on the comments said even 8 VRAM work with 32 RAM

    • @michaelbayes802
      @michaelbayes802 14 днів тому

      @@OlivioSarikas thanks I'll give at a whirl 🙂

  • @caglisto
    @caglisto 11 днів тому

    Could you make a new review on Invoke AI 5.3? I think they have FLUX as well as all the other stuff from before.

  • @scitechaiutopia
    @scitechaiutopia 14 днів тому

    Is this trained on schnell or dev or 1.1 pro? It has big file size. Could this also have a lot of anime characters from say, Dragon ball? I had tested a lot of characters on Dalle 3 in the past, and it perfectly understood a lot of them, including unexpected ones. Is Flux also trained like that? What is best upscaler for photorealistic landscape images? Currently all upscalers(except online AI services that cost a bank) totally ruin landscape images, nothing seems to work.

  • @hleet
    @hleet 15 днів тому

    nice to know❤

  • @Gli7chSec
    @Gli7chSec 15 днів тому

    thank you for these videos !! I would really like to make a music video from Flux how would you make a Music video using flux ?

    • @Elwaves2925
      @Elwaves2925 15 днів тому

      Create still images with Flux of the first frame of each scene you want in your video. Then use one of the image to video services to generate the clips. Finally, use a video editor to edit and bring it all together with the music.

    • @Gli7chSec
      @Gli7chSec 15 днів тому

      @@Elwaves2925 I need to be able to create the videos for free open source like flux in forge

    • @ApexArtistX
      @ApexArtistX 15 днів тому

      I will post tutorials on that in my channel

  •  15 днів тому

    Thanks . This is always so helpful and top news. Just discussion patreon support with my firm. I think this is a done deal.

  • @---David---
    @---David--- 14 днів тому

    What is the difference in speed between Shuttle and Schnell?

  • @SPOOKEXE
    @SPOOKEXE 15 днів тому

    wicked

  • @jimdelsol1941
    @jimdelsol1941 15 днів тому

    Hi !
    Is it a refined model already or can we expect a fine tuned version on CivitAI of it soon ?

    • @fr0zen1isshadowbanned99
      @fr0zen1isshadowbanned99 14 днів тому

      Someone was talking about a smaller Model already in the Comments. I find it for you.
      "shuttle-3-diffusion-Q4_K_S.gguf. Memory A: 7.68 GB, R: 8.53 GB, Sys: 9.7/12 GB (80.6%) on GPU 3060 12 GB"
      For other "refinements", I can't say anything, but I would love some more "Adult Content" with it. So far I am the most impressed I ever have been with any Model!!!!!!!!!

    • @jimdelsol1941
      @jimdelsol1941 14 днів тому

      @@fr0zen1isshadowbanned99 Hi ! Thank you ! ^^
      I'm more looking forward towards models trained on this but with better images or a specific style. I guess we will see some on civitai soon.

  • @vincdivine
    @vincdivine 8 днів тому

    what make shuttle 3 diffusion model amazing is its license, it Apache!!!

  • @lounatic8369
    @lounatic8369 9 днів тому

    I woul be more interested in quality then speed. I would love to get 1.1 pro quality local. Thats a video i would be interested in. Just in case ...

  • @xjasm0
    @xjasm0 15 днів тому +3

    You are a great communicator and educator :) Thanks for the work you put into these

  • @stefanb7015
    @stefanb7015 15 днів тому +13

    I prefer the look of the FLUX images, as shuttle ones look overtrained(?)

    • @TheMadManTV
      @TheMadManTV 15 днів тому +1

      yes.

    • @TheBann90
      @TheBann90 14 днів тому +1

      Disagree. It's better than flux schnell imo. But then again, who uses schnell anyway? Schnell is also a couple of months old now.

    • @Wyn3e
      @Wyn3e 10 днів тому

      @@TheBann90”who uses schnell” i could see a lot in different AI servers 👍

  • @yasirjaved-lc4yc
    @yasirjaved-lc4yc 14 днів тому

    How to turn on gpu weight

  • @Tokaint
    @Tokaint 14 днів тому

    Why does every UA-cam ignore vram and speed as if that's not the most important thing we'd want to know first? Because of watch time 😑

    • @OlivioSarikas
      @OlivioSarikas  14 днів тому

      because I don't have 10 computers to benchmark it on different configurations. Where would I find the Vram and Speed for each new model on release?

    • @Tokaint
      @Tokaint 14 днів тому +2

      @OlivioSarikas the speed difference between the 2 models you're comparing, and the minimum vram requirements. You say "it's super fast" and half way through the video still didn't make clear how fast. Comparing generations is great for new model, but so is speed and vram requirements.

    • @OlivioSarikas
      @OlivioSarikas  14 днів тому

      @@Tokaint it uses 4 steps - that's what i mean by fast. especially for that quality. how long 4 steps take depends on your system

  • @DataJuggler
    @DataJuggler 15 днів тому

    0:05 I was told if I can't say something nice, don't say anything at all. I am doing _______

  • @DarioToledo
    @DarioToledo 15 днів тому +1

    Time to discard Schnell ultimately, I see.

  • @ApexArtistX
    @ApexArtistX 15 днів тому +2

    Don’t need fast need 6 vram flux not gguf

  • @qpqpqpqpqpqpqp
    @qpqpqpqpqpqpqp 15 днів тому +2

    same plastic

  • @CosmicOrion
    @CosmicOrion 13 днів тому

    Not works for me, using forge and 32gb ram with rtx 3090, im using same textcoders/vae but forge is crashing every generate with this model
    Extra test note: This model is incredibly insufficient with 32 GB RAM and it locks the system. It also destroyed the virtual HDD memory along with 100% VRAM and 100% RAM usage. It seems that above 32GB should be used with 64GB RAM if possible.
    "For shuttle 3 diffusion" not other shuttle models.