Depth-Anything for A1111 and InstantID

Поділитися
Вставка
  • Опубліковано 17 гру 2024

КОМЕНТАРІ • 83

  • @OlivioSarikas
    @OlivioSarikas  10 місяців тому +2

    #### Links from the Video ####
    Depth Anything Model Link: github.com/Mikubill/sd-webui-controlnet/discussions/2549
    Unofficial implementation of InstantID for ComfyUI (pain to get to run at the moment of video release): github.com/ZHO-ZHO-ZHO/ComfyUI-InstantID
    depth-anything.github.io/
    huggingface.co/spaces/LiheYoung/Depth-Anything
    github.com/InstantID/InstantID?tab=readme-ov-file
    huggingface.co/spaces/InstantX/InstantID

  • @michaellorne5326
    @michaellorne5326 10 місяців тому +2

    Thank you Olivio!
    3:12 "The first time you going to use this it is going download two different models 1.5gb each"
    For those of us who are bandwidth challenged, this is a really nice thing to know and I REALLY appreciate the quick FYI. Thank you!

  • @haofanwang9914
    @haofanwang9914 10 місяців тому +14

    Thanks for introducing our InstantID!

  • @Gwenyria
    @Gwenyria 10 місяців тому +8

    Yay again something new for automatic1111 :D I still am to lazy to proper learn comfy UI and secretly hope that most of the comfy features come sooner or later also to Automatic1111

  • @CoconutPete
    @CoconutPete 9 місяців тому

    never noticed depth anything until I randomly stumbled upon it last night... this should make a difference in some of my images I've been struggling with

  • @ANGEL-fg4hv
    @ANGEL-fg4hv 10 місяців тому +32

    Well welll must've hurt coming back you traitor. Automatic 1111 Stan Here 😢

  • @Steamrick
    @Steamrick 10 місяців тому +7

    For SDXL, the diffusers_xl_depth_full depth model seems to pair well with the preprocessor. I've only tried two image inputs, but they were challenging ones and the other depth models for SDXL didn't seem up to the challenge.

  • @JohnVanderbeck
    @JohnVanderbeck 10 місяців тому +2

    InstantID looks very interesting and promising. I love anything that gives me more control. Will need to try it out

  • @nikolesfrances1532
    @nikolesfrances1532 10 місяців тому

    I saw these come out and couldnt figure out how to set it up and been looking into the lack of content and direction with both of these softwares, like a prayer our shepard Olivio riegns down and deliviers! Thank You

  • @joehogans4494
    @joehogans4494 10 місяців тому +1

    Awesome thanks Olivio! Depth Anything Model, it's definitely also a bad hands, leg, body resolver for me as well.

  • @gimperita3035
    @gimperita3035 10 місяців тому

    Thanks for the research, Olivio. As always.

  • @NuKeBoX-NKBX
    @NuKeBoX-NKBX 10 місяців тому

    Always on the hype, thanks Oliviioooo! 🐔😘

  • @FredPauling
    @FredPauling 10 місяців тому

    Depth Anything model is a huge leap in quality. Can't wait to see more advancements in monocular depth estimation.

  • @Dmitry-n7r
    @Dmitry-n7r 10 місяців тому +1

    Depth-Anything is now supported & is the default depth processor in Invoke 3.6.1

  • @benjamininkorea7016
    @benjamininkorea7016 10 місяців тому

    Very nice video as usual.
    I'm curious if there's any chance to use the sharper depth map preprocessor with older models or with the old Depth utilities. I'm interested in creating stereo images-- they used to be only so-so, but with improved sharpness, it might be worth trying again.

  • @moonduckmaximus6404
    @moonduckmaximus6404 10 місяців тому +2

    the depth map was not generated with your workflow. i had to take the result image and put it into control net and push the explosion button to generate the depth map

  • @moviecartoonworld4459
    @moviecartoonworld4459 10 місяців тому

    Thank you for sharing the latest information!!! ^----^

  • @magenta6
    @magenta6 10 місяців тому +2

    "As soon as I get my hands on it!"

  • @Vargol
    @Vargol 10 місяців тому

    Hi All, be warned that if you try to do photo or cinematic styles with InstantID you get Getty watermarks on ~ 50% of your images.
    That's probably the reason those styles are missing from the HF spaces demos.

  • @paulsheriff
    @paulsheriff 10 місяців тому +1

    might want to mention the file name must still be named control_sd15_depth_anything.safetensors or it will not be reconised

  • @jonmichaelgalindo
    @jonmichaelgalindo 10 місяців тому

    Please post an update for instandID once it's working in A1111 / Comfy! ❤

  • @EarmWermChannel
    @EarmWermChannel 10 місяців тому

    Game changer. Load up an old 3D scene, remove all textures and lights, prompt what you want. Bingo.
    The only downside is that it runs on 1.5 models only. So using Krea to upres to 4k

  • @NaitorStudios
    @NaitorStudios 10 місяців тому

    Please make a tutorial about Depth-Anything standalone, specially for video and photo editing outside Stable Diffusion

  • @film-alchemist
    @film-alchemist 8 місяців тому

    When trying to generate the depth map I'm getting this error: "ValueError: controlnet is enabled but no input image is given" Any ideas?

  • @humabt4
    @humabt4 10 місяців тому

    Does anyone know the notebook for comfy ui. I had tried a bunch of notebooks but they didn't work on the Amazon sage runner?

  • @Semi-Cyclops
    @Semi-Cyclops 10 місяців тому +4

    is it only for 1.5 not XL?

    • @Steamrick
      @Steamrick 10 місяців тому +1

      It seems there's only a SD1.5 controlnet model so far.
      Of course you're welcome to try the preprocessor with any of the existing SDXL Depth models. In a quick check, diffusers_xl_depth_full seems to work pretty well with it.

  • @boyblue80
    @boyblue80 6 місяців тому

    you say you must rename the file, but its a folder not a file..so which file within t hat folder must be renamed? or does the folder itself have to be named 'control_sd15_depth_anything' ?

  • @fjccommish
    @fjccommish 9 місяців тому +1

    Stunning? It makes head shots. That's it.

  • @OurResistance
    @OurResistance 10 місяців тому

    Hey. Why is there no way to convert the depth map into a SBS image? I looked everywhere!

  • @anthony_leckie
    @anthony_leckie 10 місяців тому

    Thank you, Olivio.

  • @hamedsadeghizadeh6660
    @hamedsadeghizadeh6660 10 місяців тому

    Hi Olivio, thank you for your videos. Is need to download the Depth-anything/checkpoints, if yes, which one and where should i put them? Sorry if my question is so noobie.

  • @kernsanders3973
    @kernsanders3973 10 місяців тому

    cool been waiting for this to come to A1111 EDIT: Ah rats thought from the title that InstantID was now in A1111... Guess the waiting continues
    The new depth processor is great, anything non realitic/3D was hit and miss with normal depth. This new one certainly feels like there are more hits than miss.

  • @matthallett4126
    @matthallett4126 10 місяців тому +1

    There's a Adapter Face ID controlnet you can experiment with in A1111. I tried it with my own face, and it did OK, but the checkpoint you use makes a big difference.

    • @Elwaves2925
      @Elwaves2925 10 місяців тому

      You likely can't post a link because it's YT but can you help by pointing me in the right direction of where to look for it? Last time I searched for A1111 and FaceID I found nothing. Cheers.

    • @matthallett4126
      @matthallett4126 10 місяців тому

      @@Elwaves2925 Huggingface / IP Adapter FaceID /

    • @bunnystrasse
      @bunnystrasse 10 місяців тому

      Where

  • @svenvarg6913
    @svenvarg6913 10 місяців тому

    How does this compare with Marigold Depth estimation and does this new depth model provide relative or absolute depth?

  • @mayorc
    @mayorc 10 місяців тому

    Instant ID is the same tech as that in PhotoMaker from TencenArc or an improvement over that?

  • @JoeBurnett
    @JoeBurnett 10 місяців тому

    Your tutorials are so good! Thank you!

  • @8eck
    @8eck 10 місяців тому

    Just wow, i remember how slow it was a few years ago. I think i was using MiDaS project at that time.

  • @Veselin_Angelov
    @Veselin_Angelov 10 місяців тому

    Two months ago: IP Adapter comes out.
    Five days ago: Photomaker comes out!
    Today: InstantID comes out!
    However, even after an InstantID extension comes out for A1111, I don't think Photomaker will fall into obsolescence, because I didn't see a feature where ImstantID can merge features.
    Therefore: Photomaker to "bash" facial features into a new image, and then InstantID to reuse the synthetic face, equals consistent characters from reference? (I wonder if feature-bashed synthetic faces are ethical? Seriously. Any thoughts?)

  • @sentinelah7
    @sentinelah7 10 місяців тому

    Thank you very much!

  • @moonduckmaximus6404
    @moonduckmaximus6404 10 місяців тому +1

    Finally a good ole fashioned video for automatic 1111 without mentioning .....''comfy ui''

  • @Theexplorographer
    @Theexplorographer 10 місяців тому

    Excellent, thank you.

  • @MS-gn4gl
    @MS-gn4gl 10 місяців тому +8

    Why would anyone be surprised tiktok has ai projects? They've literally been building some of the most effective realtime AI tools for their filters for at least the last 4 to 5 years.

    • @wykydytron
      @wykydytron 10 місяців тому

      Filters don't use ai, it's simple face detection algorytm

    • @LokeKS
      @LokeKS 10 місяців тому +1

      @@wykydytron face detection is ai, haha

  • @borutesufaibutv1115
    @borutesufaibutv1115 10 місяців тому

    Depth color reminds me if lens blur from LrC haha

  • @ipwnzuall2000times
    @ipwnzuall2000times 10 місяців тому

    genAI is moving so fast...i haven't gotten my head around segment anything yet and now this

  • @hyrokon5767
    @hyrokon5767 10 місяців тому +1

    the amount of tab opened 😮 😢

  • @ImmacHn
    @ImmacHn 10 місяців тому +3

    News on this depth-map for comfy?

    • @OlivioSarikas
      @OlivioSarikas  10 місяців тому +1

      Apparently it was updated in controlnet there also, but i didn't have time to check yet.

  • @richardgreaney
    @richardgreaney 10 місяців тому

    Those of us using CPU-only, this preprocessor won't work. It seems like it requires xformers, which requires an Nvidia GPU :(

  • @Airbender131090
    @Airbender131090 10 місяців тому

    2 bad this update broke animatediff in A1111...that was the reason i updated in a first place...

  • @goliat2606
    @goliat2606 10 місяців тому

    I generated woman face that i very like. Is any way to apply this face to rest of images which i will generate? Reactor or other face replace nodes makes face very bluury when image is bigger than 512x512.

  • @sherpya
    @sherpya 10 місяців тому

    we need a comparison with photomaker

  • @mame947
    @mame947 10 місяців тому +1

    can comfyui use the depthanything and instantID?

  • @PawFromTheBroons
    @PawFromTheBroons 10 місяців тому

    It's kinda weird of the developer to ask for its own file on GitHub to be renamed to something more sensible, while they could just as well provide said file with its proper name.
    😆

  • @timtarbet4594
    @timtarbet4594 10 місяців тому

    Is this coming to Comfy?

  • @simpleandfrank
    @simpleandfrank 10 місяців тому +4

    I need a new PC...

  • @SoCalGuitarist
    @SoCalGuitarist 10 місяців тому +1

    1.5 only? that's disappointing.

    • @OlivioSarikas
      @OlivioSarikas  10 місяців тому

      yes, but you can upscale in SDXL, so that's kind of a work around

  • @saschascharf2932
    @saschascharf2932 10 місяців тому +2

    Taylor Swift is THE face of AI image generation. ;)

    • @Bahamamos
      @Bahamamos 10 місяців тому +2

      Actually it’s an Asian face early on…

  • @sinayagubi8805
    @sinayagubi8805 10 місяців тому +7

    We need this for Comfy, I'm not comfy with A1111

  • @MilesBellas
    @MilesBellas 10 місяців тому

    oh no.....
    TT !!!!!

  • @artistaartificial5635
    @artistaartificial5635 10 місяців тому

    O:

  • @Orangeduck
    @Orangeduck 10 місяців тому

  • @angloland4539
    @angloland4539 10 місяців тому