Throwing data to your face (models)!

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ม.ค. 2025

ความคิดเห็น • 113

  • @0x20d
    @0x20d 11 หลายเดือนก่อน +107

    Matteo, I think I speak for many of us in the community: Your content f'n rocks. Thank you so much for taking the time and explaining all the nitty gritty details of IPAdapter and how to use it to create consistent results. Please keep doing what you're doing.

    • @blacksage81
      @blacksage81 11 หลายเดือนก่อน +2

      You're speaking for me.

    • @TheLazyAI
      @TheLazyAI 11 หลายเดือนก่อน +1

      And me!​

    • @rod-me8ey
      @rod-me8ey 11 หลายเดือนก่อน +1

      You don't speak for me, these tutorials are painful to watch lol.

    • @binichnich8517
      @binichnich8517 11 หลายเดือนก่อน

      Yes yes yes!!

    • @AhmedAmineHomman
      @AhmedAmineHomman 9 หลายเดือนก่อน

      I wholeheartedly agree. It's been a long time since I've not been so enthusiastic about TH-cam videos. You ROCK Matteo !

  • @jlyonia
    @jlyonia 9 หลายเดือนก่อน +4

    I'd also like to give voice to the many people saying your content is amazing. It truly is. The rocket ship from learner to intermediate and beyond. You explain the "why", not just show an example of "how" with a click-bait title and an enticing misleading thumbnail. Thank you. Please don't stop making this content, whatever the platform you choose to publish it on. It is fantastic.

  • @Foolsjoker
    @Foolsjoker 11 หลายเดือนก่อน +23

    That is some high quality spaghetti right there. Compliments to the chef!

  • @gibsoncrypto1557
    @gibsoncrypto1557 11 หลายเดือนก่อน +9

    Your are new member of GOAT ComfyUi workflow Creator

  • @crazydiamond3757
    @crazydiamond3757 2 หลายเดือนก่อน

    Sto workflow Sta a pija consapevolezza di se stesso co tutte quelle sinapsi

  • @norvsta
    @norvsta 11 หลายเดือนก่อน +3

    Brilliant stuff. Thanks so much for taking the time to produce these tutorials Matt3o 🙂

  • @ArielTavori
    @ArielTavori 11 หลายเดือนก่อน +6

    Community MVP! 🙏🏻

  • @beveresmoor
    @beveresmoor 11 หลายเดือนก่อน +2

    Your videos always give me some information I don't think I need to know before. Thank you for your hard work. 😊

  • @eucharistenjoyer
    @eucharistenjoyer 11 หลายเดือนก่อน +2

    Another amazing video Matteo, direct, to the point and with great didactics, God bless you!

  • @denisquarte7177
    @denisquarte7177 11 หลายเดือนก่อน +1

    I am at the start of your video, it feels like a sportevent :'). ComfyUI can be quite daunting sometimes, but this... this is entertainment. Great content and many thanks.

  • @Sergio-ds3sq
    @Sergio-ds3sq 4 หลายเดือนก่อน

    Many thanks for your videos friend, they're awesome!
    Looking forward for the 2 people video please!

  • @TheBestgoku
    @TheBestgoku 11 หลายเดือนก่อน

    wow, what a great scientific approach. Love your style and obsession with this. i respect you

  • @priyadarshandeshmukh8283
    @priyadarshandeshmukh8283 11 หลายเดือนก่อน +1

    Hands down the best content of comfiui in my view

  • @reapicus557
    @reapicus557 9 หลายเดือนก่อน

    I've been able to make some amazing progress by following along with your videos. Thank you very much!

  • @moviecartoonworld4459
    @moviecartoonworld4459 11 หลายเดือนก่อน +1

    Thank you for always providing great lectures! I am learning a lot from the detailed and friendly explanations. Thank you again.

  • @hleet
    @hleet 11 หลายเดือนก่อน

    Thanks for taking the time to make theses tutorials. Very hard stuff to understand but I'll keep trying :)

  • @willhamlam
    @willhamlam 11 หลายเดือนก่อน

    Best tutorial and best explaination ever, very great video, also very inspiring.

  • @pfbeast
    @pfbeast 11 หลายเดือนก่อน +3

    Thank you for this video👍👍👍, again very in-depth tutorial in simple language ❤❤. I have 1 request - Please upload in-depth prompting tutorial video for comfyUI

    • @ArielTavori
      @ArielTavori 11 หลายเดือนก่อน

      +1

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +2

      thanks!
      prompting is such a complex topic and really depends a lot on the kind of image you are trying to do... but it would make a very interesting video for sure.

    • @pfbeast
      @pfbeast 11 หลายเดือนก่อน

      @@latentvision i will wait for your video on this topic.❤️

  • @lambgoat2421
    @lambgoat2421 11 หลายเดือนก่อน

    that workflow looks crazy!

  • @uv10100
    @uv10100 11 หลายเดือนก่อน

    These videos are golden. Please keep going.

  • @GameOfCards
    @GameOfCards 11 หลายเดือนก่อน +3

    Another HQ video from Mateo about Stable Diffusion? Yes, please! 😊

  • @OscarLindahlofficial
    @OscarLindahlofficial 11 หลายเดือนก่อน

    Awesome as always!!! Thank you Matteo!

  • @substandard649
    @substandard649 11 หลายเดือนก่อน

    As always, excellent and inspiring content. Thank you

  • @MarkRiverbank
    @MarkRiverbank 11 หลายเดือนก่อน +1

    Something I’ve done for upscaling with 1.5 models is to go back to the original model and separately add the IPAdapter(s) and Lora with full 100% weights for the upscaler-so lower weights on the model going into the first ksampler so it’s not too rigid, but high weights on the upscale to pull it closer to the sample image.

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +3

      yes that's a good strategy especially when you have multiple people or when the image is not a portrait. Always better to make a rough composition first and refine in a second pass

  • @c0nsumption
    @c0nsumption 11 หลายเดือนก่อน +1

    Matteo, thank you so damn much for your outstanding work. I have been on a deep dive on all your work, clip models, and diffusers

  • @bigdaddy5303
    @bigdaddy5303 11 หลายเดือนก่อน

    Matteo - one thing I'd love to know, is how the base checkpoints determine the faces (without ipadapter). What I mean, is almost every checkpoint I have tried has a "base" female or male face. Even when changing the nationality or race, the face characteristics stay similar to that base face. It's only when you start adding names or other positive prompts can you change the face into something more unique. I understand the models were trained on common sets of portraits, but surely there were many thousands of faces, if not millions. Ideally in my workflow I want to create a never before seen face, then use a workflow such as this to put the character into different scenes, poses. However I just can't seem to to randomise the face enough without putting in lots of ugly looking prompts.

  • @NicolaTomassoni
    @NicolaTomassoni 11 หลายเดือนก่อน

    Sempre video top!

  • @danilsi6431
    @danilsi6431 11 หลายเดือนก่อน

    Thank you🙏, very useful analytics and a tremendous amount of work done👷.

  • @Mehdi0montahw
    @Mehdi0montahw 11 หลายเดือนก่อน +3

    like magic

  • @draken5379
    @draken5379 11 หลายเดือนก่อน

    Great video as always man !😀

  • @RamonGuthrie
    @RamonGuthrie 11 หลายเดือนก่อน

    These videos are great, thank you!

  • @ohheyvoid
    @ohheyvoid 10 หลายเดือนก่อน

    Awesome!!! So helpful. Thanks!

  • @francaleu7777
    @francaleu7777 11 หลายเดือนก่อน

    thank you very much Mateo

  • @kikoking5009
    @kikoking5009 7 หลายเดือนก่อน

    Hi Mateo 👋
    About changing the Hair.
    Using Unsampler with Controlnet would change the colour with keeping the same hair exactly , when writing in a prompt another colour. Right?
    instead of masking or inpainting

  • @noonesbiznass5389
    @noonesbiznass5389 8 หลายเดือนก่อน

    Loved the video! Given your experience in this space, are you aware of any tech that will improve upon inswapper/insightface etc to enable swapping of faces or generation of custom faces at side or angles other than front-on or nearly front-on? this seems to be largest constrain of the current tech. Thx!

  • @lawalexlaw
    @lawalexlaw 11 หลายเดือนก่อน

    Crazy good inspiration

  • @rod-me8ey
    @rod-me8ey 11 หลายเดือนก่อน

    I love how the name of the models overlap the interface and become completely unintelligible. Good stuff. Remarkable UI design.

  • @Paulo-ut1li
    @Paulo-ut1li 11 หลายเดือนก่อน

    Wow, another great video Matteo! I would love to see your take on the new PhotoMaker and InstantID SDXL models.Peace!

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      I'm trying PhotoMaker right now... not impressed at the moment. InstantID has potential.

  • @alexgilseg
    @alexgilseg 11 หลายเดือนก่อน

    amazing! thank you 🙏🙏🙏

  • @tartwinkler1711
    @tartwinkler1711 11 หลายเดือนก่อน

    Great video, learned a lot!

  • @0A01amir
    @0A01amir 11 หลายเดือนก่อน

    Amazing video Thank you.
    For me the best result is FaceID v2 SDXL+Upscale but sadly that truns my comfyui into a lowvram mode, i guess there was a deleted FaceID sdxl, it ran fine and results were really good.

  • @KunjaBihariKrishna
    @KunjaBihariKrishna หลายเดือนก่อน

    Have I finally found the holy grail of stable diffusion youtube

  • @musty5551
    @musty5551 11 หลายเดือนก่อน

    From what I saw SD15 FaceIDv2 + 2x upscale works incredibly well (upscale as simple resample with 0.4 denoise). Adding any other face model makes face blurry. With FaceIDv2 its incredibly sharp and keeps level of "likeness" comparable to best lora.

    • @eucharistenjoyer
      @eucharistenjoyer 11 หลายเดือนก่อน

      Can you go a bit further on what you mean by upscale as simple resample? Thank you!

    • @unityofiranian1296
      @unityofiranian1296 11 หลายเดือนก่อน

      I think it's the upscale mode you can choose
      Like in default it's on (near exact)

  • @DataLeveling
    @DataLeveling 11 หลายเดือนก่อน

    Great work!

  • @DarioToledo
    @DarioToledo 11 หลายเดือนก่อน +2

    To say that it's at least a month that I'm implementing two faceIDs in the same image, didn't know that it's been frequently asked on discord, you have clearly explained how to do it in other videos after all. Anyway, thanks A LOT for these benchmarks, these really are a time saver. Guess I'll stick to faceIDv2 and reactor faceswap in the end for total consistency of my characters. The faceID is still useful for hair and face shape.

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      yeah we already talked about that... you know, on internet something said 1 month ago doesn't matter anymore 😄

  • @HiProfileAI
    @HiProfileAI 7 หลายเดือนก่อน

    Im trying to follow along with the new pul ID demo but am unable to see the DLib Model for Face Analysis Module. Only the insigt face model shows up. Where do we place the Dlib Models as I have downloaded them but they are not showing up in the load model. Thanks

  • @HiProfileAI
    @HiProfileAI 7 หลายเดือนก่อน

    Did you try the pony model or any pony modles for face recognition in your tests.? If not I'd like to see you do that next time around to compare how that model fares in face recognition.

    • @latentvision
      @latentvision  7 หลายเดือนก่อน +1

      pony models are not compatible in general

    • @HiProfileAI
      @HiProfileAI 7 หลายเดือนก่อน

      @@latentvision Okay makes sense.

  • @paulotarso4483
    @paulotarso4483 10 หลายเดือนก่อน

    Hey, your tutorials are awesome. How can I use the FaceID Portrait workflow into an existing image? e.g. just a simple faceswap of an existing image, maybe using Inpainting or something? What do you recommend, is there an existing workflow where I can set the face images, and the image to be swapped?

    • @latentvision
      @latentvision  9 หลายเดือนก่อน +1

      you can do inpainting sure, or you can bbox the face and do a simple image to image

    • @paulotarso4483
      @paulotarso4483 9 หลายเดือนก่อน

      Thank you so much! How would bbox face and i2i work? Am I outpainting the original face into a new image, or something else?
      Also, is FaceID the highest fidelity for photorealism, or InstantID can also work with photorealism?
      Thanks!!@@latentvision

  • @crazyfaint
    @crazyfaint 11 หลายเดือนก่อน

    Im new to all this, its there any way to make the head tilt or show a different facial expression?

  • @TheDoranMaster
    @TheDoranMaster 11 หลายเดือนก่อน

    BRAVO 👏 🙌 🎉

  • @DanielPartzsch
    @DanielPartzsch 11 หลายเดือนก่อน +1

    Great benchmark, thanks a lot. You said that Instant ID and Face ID portrait rely on insightface, thus you need to buy a license for commercial use. Does this also apply to using Apply ip adapter face ID then as it is also using insightface? Thanks again.

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      it's not the node itself, it's the insightface model. If you don't use the model for the image generation, no problem

    • @DanielPartzsch
      @DanielPartzsch 11 หลายเดือนก่อน

      @@latentvision thanks. But for my understanding and to double check: doesn't the node use the model under the hood?

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      @@DanielPartzsch if you use any FaceID model, then yes, those make use of insightface. You should check their license. If you don't use any of the FaceID models, then you are fine.

    • @aliyilmaz852
      @aliyilmaz852 9 หลายเดือนก่อน

      sry if it is a dumb question, but how they can identify if somebody used their insightface by looking at the production image?

  • @HakanBulut
    @HakanBulut 11 หลายเดือนก่อน

    Is it possible to apply makeup on an input image without using a checkpoint? I've been working on this for a long time but I'm not sure if my efforts are in vain.

  • @vladik210
    @vladik210 11 หลายเดือนก่อน

    How do I calculate the embedding differences of my workflows? I want to see if I recreate the same individual at the end. Thanks!

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +2

      I'll add a node for that

  • @yoda5477
    @yoda5477 6 หลายเดือนก่อน

    Hi,
    @Latent Vision How do you use multiple attention mask when you have multiple reference photos ?

    • @latentvision
      @latentvision  6 หลายเดือนก่อน +1

      there's a video about attention masking!

    • @yoda5477
      @yoda5477 6 หลายเดือนก่อน

      @@latentvision my bad i thought the mask was for what is considered on the input! But it is for what is influence on the output ! Sorry

  • @PradeepKumar6
    @PradeepKumar6 11 หลายเดือนก่อน

    Amazing video, one question , what is the difference between weight and weight_v2? @5.43 , he mentioned these weights, but I am unable to understand, can someone help?

    • @latentvision
      @latentvision  11 หลายเดือนก่อน

      weight is the global weight. weight_v2 is used for the clip vision embeds. I suggest a value between 1.5 and 2

  • @goliat2606
    @goliat2606 10 หลายเดือนก่อน

    So for commercial use only Plus Face and Full Face are allowed?

  • @DKAS-g4h
    @DKAS-g4h 11 หลายเดือนก่อน

    Thanks!
    Is PhotoMaker is different separate model?

    • @latentvision
      @latentvision  11 หลายเดือนก่อน

      yeah completely different thing.

  • @StudioOCOMA2D3D
    @StudioOCOMA2D3D 10 หลายเดือนก่อน

    Hi and thank you for your splendid video.
    Does anyone know why i have this error please?
    ---
    Error occurred when executing InsightFaceLoader:
    No module named 'insightface.app'
    ---
    I've proceeded with the install inside ComfyUI via Git Url and everything was correct but i cannot test InsightFace.
    Thank you in advance.
    Olivier

  • @zzzzzzz8473
    @zzzzzzz8473 11 หลายเดือนก่อน

    such good information here , thanks for the research ! one thing that might be nice is establishing a baseline , using actual photos of the same person in different scenarios to see how low the difference tends to be with realife variation

  • @ChanhDucTuong
    @ChanhDucTuong หลายเดือนก่อน

    It’s been 9 months, how are these techniques compare to newer ones like PulID please? Thank you for sharing.

    • @latentvision
      @latentvision  หลายเดือนก่อน +1

      in most recent videos I talked about Pulid and others

  • @PeterLunk
    @PeterLunk 11 หลายเดือนก่อน

    Awesome demo Mateo !!!
    Respect.
    #NeuraLunk

  • @drmuradkhan
    @drmuradkhan 11 หลายเดือนก่อน

    Awesome title

    • @latentvision
      @latentvision  11 หลายเดือนก่อน

      IKR?! It basically wrote by itself!

  • @BigSnoots
    @BigSnoots 11 หลายเดือนก่อน +1

    Best videos on TH-cam with respects to Comfy! A few videos that I think would help others (including myself) is inpainting with SDXL and photo bashing on SDXL. I find inpainting with SDXL inconsistent. It would be nice to see these topics covered in images that are geared towards landscapes and not just on people. Such as adding objects to a scene where prompting alone can't handle it because you are adding several objects. Just my two cents and your channel is just awesome!

    • @nicolascampailla
      @nicolascampailla 11 หลายเดือนก่อน

      Ferniclestix has some great tutorials about those! Him and matt3o have some of the best comfy tutorials

  • @somtoachu5704
    @somtoachu5704 11 หลายเดือนก่อน

    thanks man this helped

  • @JJCAFE_RAinly
    @JJCAFE_RAinly 11 หลายเดือนก่อน

    위와같이 모델 헤어도 일률적으로 비슷해질까요?

  • @AndiSaleh
    @AndiSaleh 11 หลายเดือนก่อน

    Matteo, can you confirm that this only works when the positive conditioning is plugged directly to the sampler, i.e.: it breaks when using concat/combine with another positive prompt?

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      no, it should always work. Of course more conditionings will pollute the composition

    • @AndiSaleh
      @AndiSaleh 11 หลายเดือนก่อน +1

      @@latentvision You're right, I guess that was the case. Had to bump up the prompt for it to take effect again. Thanks 👍

  • @AkkadianMystique
    @AkkadianMystique 11 หลายเดือนก่อน

    treasure

  • @Kentel_AI
    @Kentel_AI 11 หลายเดือนก่อน

    Thanks

  • @ALatentPlace
    @ALatentPlace 11 หลายเดือนก่อน

  • @GameOfCards
    @GameOfCards 11 หลายเดือนก่อน

    I'm struggling when I want a specific eye color, especially the abnormal colors. Any tips?

    • @latentvision
      @latentvision  11 หลายเดือนก่อน

      well inpainting is the easiest solution

    • @sherpya
      @sherpya 11 หลายเดือนก่อน

      try adding heterochromia in the prompt

  • @heggy_fpv
    @heggy_fpv 10 หลายเดือนก่อน

    Did anyone figure out how to run insightface with cuda instead of cpu?

    • @latentvision
      @latentvision  10 หลายเดือนก่อน

      leave insightface in the CPU, you don't need to bother the GPU for feature extraction

  • @sharky0817
    @sharky0817 11 หลายเดือนก่อน +2

    Don't get me wrong but... can I get your aunties number? I'll help her carry the groceries!

  • @procrastonationforever5521
    @procrastonationforever5521 22 วันที่ผ่านมา

    Emotions still looks creepy, lol :)

  • @kawa9694
    @kawa9694 11 หลายเดือนก่อน

    for unrealistic character (anime) ,🥲 its bad

    • @latentvision
      @latentvision  11 หลายเดือนก่อน +1

      you need more work, but it works for that too