How to use PuLID in ComfyUI

Подписаться 20 тыс.

Просмотров 20 тыс.

50% 1

In this video I'm going through some basic PuLID usage and also comparing it to other face models. If you have it already installed remember to upgrade the extension!
PuLID ComfyUI extention: github.com/cubiq/PuLID_ComfyUI
Face Analysis node: github.com/cubiq/ComfyUI_Face...
Github sponsorship: github.com/sponsors/cubiq
Support with paypal: www.paypal.me/matt3o
Twitter: / cubiq
My Discord server: / discord
Workflows: f.latent.vision/download/puli...
00:00 Intro
00:31 Basic Usage
02:41 Improve image with face analysis
05:59 Face detailer
11:16 Advanced node
13:35 Style transfer and attention masking
16:10 Comparing face models
16:35 Comparison PuLID
17:02 Comparison FaceID
17:52 Comparison PhotoMaker
18:06 Comparison FaceID Potrair Unnorm
18:32 Comparison InstantID

Наука

Опубликовано:

30 май 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 176

@miranteazi 18 дней назад

Always a banger, even though your tutorials are more about new nodes, I always learn something new about the models behavior

@jccluaviz 18 дней назад

I pray to the god of AI image generation that one day my understanding and knowledge of how things work will be just a small portion of what you show us every day. I just have to say... MASTER !!! Supreme work.

@ttul 18 дней назад

Another incredible result from Matteo!

@DavidRoyPennCollazos 18 дней назад

Valuable stuff here! Appreciate the Face Analysis Model, wasn't even aware that was a thing!

@Mranshumansinghr 16 дней назад

The Combination of Pulid and FaceID is amazing. I am using Pulid for Expression and FaceID for Face.

@Renzsu 18 дней назад

Dude, every video of yours is a goldmine. A subscribe should come by default with every download of anything SD!

@pn4960 18 дней назад

Consistent, useful, clear explanation

@BruceMorgan1979 18 дней назад

Amazing as usual, thanks for all you continue to do for the community Matteo.

@AI_Popcorn 17 дней назад

Absolutely amazing as always- Thank you!

@swannschilling474 18 дней назад

Thanks so much for this great workflow!! 🎉🎉🎉

@AhmedAmineHomman 14 дней назад

Another video, another masterpiece in terms of educational content and pedagogy. You're the best!

@Joostered 17 дней назад

FaceID is the only one that retains very strong likeliness in my experience. Specifically so the deprecated strong sd15-only model. Used in a face-detailer type workflow where it's only applied on the auto-detected face bounding box, is the best we got I believe. If only it could follow facial expressions.

@uk3dcom 18 дней назад

Amazing work and very helpful tutorial. Now my brain aches... but excited to try these workflows.

@goodie2shoes 18 дней назад

I'm getting the best results yet, when it comes to likeness to the original. Great work as usual, Matteo!!!

@latentvision 17 дней назад

just doing my part!

@oredzera 18 дней назад

Just what i want !!! you are legend!

@neofuturist 18 дней назад

First, let's go!!! thanks for all your work Matteo

@latentvision 18 дней назад

damn you are fast!

@urgyen9689 18 дней назад

Thank you very much for a new toy and its detailed tutorial 👍👍👍

@KDawg5000 18 дней назад

Awesome! Can't wait to try it out.

@3stdv93 18 дней назад

Looks amazing! 😍

@Andro-Meta 18 дней назад

Thank you for implementing amazing nodes and for the video guides!

@ICHRISTER1 18 дней назад

Thank you Matteo! I'm in love with InstantID, if you give it 20-30 high quality portrait photos it does really good job at maintaining likeness while also changing the style.

@youtindia 18 дней назад

Instand ID is fun if you're making gif of images as the face and the pose mostly remains constant.

@daliaslay День назад

That's amazing!!! Thanks, I managed to make only 2 passes and have incredible results! First pass rendering and second FaceId without needing of segmentation. Scores are around 0.4! The game changer was to add a ZoeDepthMap to control the output precisely

@latentvision 15 часов назад

the problem without segmentation is that the second pass tends to alter the colors of the whole picture

@daliaslay 14 часов назад

@@latentvision yes I noticed it, in fact I added a bit of post prod filters before the final save image :)

@leiyangalable 4 дня назад

great work！another day of knowledge pill

@moviecartoonworld4459 15 дней назад

Thank you very much for letting me learn a good lecture.

@bipinpeter7820 18 дней назад

You always rocks! keep going

@igorkotov8937 18 дней назад

Thhhhaanks Matteo, yesterday fought with faceid set-up and voala :)

@nicolasmarnic399 18 дней назад

Hi master! Thanks, i was waiting for this workflow

@mayorc 17 дней назад

Ottimo lavoro!

@fernandomasotto 14 дней назад

thank u Matteo this is very usefull!! you are number 1

@eduger 18 дней назад

always amazing.

@pn4960 18 дней назад

Thank you for the free education 👍

@Sedtiny 18 дней назад

Matteo, you are my hero

@erdmanai 13 дней назад

Thank you so much!

@velvetjones8634 18 дней назад

Thank you!

@jomiller7332 11 дней назад

another good job !

@AlistairKarim 18 дней назад

Dude, you're awesome.

@ericruffy2124 17 дней назад

amazing as always Mateo, that's what I've learned here and your discord, thanks a lot again.

@Palalune 17 дней назад

That picture will haunt my dreams 🙂 Thanks for another great video.

@latentvision 17 дней назад

you are welcome :P

@denle637 18 дней назад

amazing good job

@sirmeon1231 18 дней назад

Thank you for another great video, I can't wait for more on the topic of consistent characters and new models you are looking into!

@genAIration 18 дней назад

My fav youtuber! ❤

@latentvision 18 дней назад

damn! I'm not a RU-vidr! :D

@genAIration 18 дней назад

@@latentvision I know I know. I am sorry then you are my fav teacher so far 😂

@tuurblaffe 18 дней назад

nice one!

@rsunghun 18 дней назад

so cool man.

@matthewharrison3813 12 дней назад

Thanks, that's great. Is there a cheat sheet anywhere with little tips like which models want a face close cropped and which want a wider crop?

@chove93 18 дней назад

thx you ! Can it work with object images, or does it only work with face images?

@antronero5970 18 дней назад

Amazing, does it work only with faces or also objects and landscapes

@GameOfCards 18 дней назад

Thanks for another great video! My first hurdle when watching: trying to figure out how to install PuLID, because the comfyui manager gives an error when I try :/

@halfd0rk 18 дней назад

Same

@Reddkomet 18 дней назад

@@halfd0rk😊

@user-marhal 18 дней назад

it helped me Please go to the custom_nodes/ComfyUI-Manager directory and execute a git pull to update it.

@futurediffusion 17 дней назад

same

@Reddkomet 17 дней назад

Same

@headscout 18 дней назад

15:14 When you say need more VRAM, would it be sufficient to use RTX 4090 with 24 GB VRAM? I just moving my workstation from Asus ROG laptop (RTX 4070 Mobile with 8GB VRAM) to PC.

@user-hw8nl6jf8k 17 дней назад

thanks

@futurediffusion 17 дней назад

how install the dlib models ?

@RuliKoto 12 дней назад

anybody?

@anandwadodkar 9 дней назад

Yes pls- anybody?

@StringerBell 17 дней назад

Why isn't the workflow included in the photo in Github?

@amaru_zeas 17 дней назад

Great video Matteo, curious what python version are you using?

@amaru_zeas 17 дней назад

(IMPORT FAILED) PuLID_ComfyU still getting this error :(

@RoN43wwq 18 дней назад

so cool

@PradeepKumar6 5 дней назад

Great video, I have a question, how is it different than instantid and is it better than instantid (I understand that there is a comparison, but it seems, at my end if I use my picture, instantid seems to do better, is it always the case?), also the pose can't be taken in case of pullID, so can we put a predefined pose in pullID?. Also a big thank you for your work. You are really doing great work. Thanks !!!

@latentvision 5 дней назад

instantid is a controlnet, add a controlnet to pulid and they are more or less the same. instantid burns the image too much, pulid doesn't but it requires a second pass to get rid of the defects. there's not a clear winner, depends on the application

@RoguishlyHandsome 18 дней назад

Does it have to be a lightning checkpoint? Would turbo work?

@aliyilmaz852 18 дней назад

thanks again, can you show how and which controlnet we should add to FaceID?

@futurediffusion 17 дней назад

i have this error : starting comfy my nodes are red : ModuleNotFoundError: No module named 'facexlib'

@dimitarmarinov1864 16 дней назад

same

@yosribengaidhassine9299 16 дней назад

I did git clone url but I dont know where I put the folder PuLID_ComfyUI

@MrPaPaYa86 16 дней назад

Question: what are the differences between pulid and ipAdapter? When to choose one over the other?

@starzilla2975 8 дней назад

This is awesome! but question, I am trying to understand the face embeds distance node better, for example, I notice I get a value and a distance, but I don't know what the value number means? Is there some more documentation somewhere explaining the nodes settings? I can't find anything!

@latentvision 7 дней назад

you are in luck, I'm posting a video about it later today

@pfbeast 18 дней назад

👌👌. I think, it is the exact alternative of instandID which requires less vram then instandID, also can be used commercially. It depends on us, which one we like to use. Am i correct?

@StringerBell 18 дней назад

Use Pulid with caution. I once didn't Pulid properly and now I have a son.

@Injaznito1 18 дней назад

🤣

@ohnoanyway1016 18 дней назад

i used to have a weak PuLID game. i still do, but i used to, too.

@swannschilling474 18 дней назад

My god so dumb, yet so funny!!!

@superlucky4499 17 дней назад

You are amazing

@latentvision 17 дней назад

no, YOU are amazing!

@tetianaf5172 17 дней назад

Hi! Thank you so much for the video and the workflow! Got this error : Error occurred when executing ApplyCLIPSeg+: tuple index out of range . Is it necessary to apply this mask?

@latentvision 17 дней назад

you can segment the face with any model you want (even manually)

@jamesyin3220 17 дней назад

Thanks for the video! Unrelated question. Is there a way to use IPAdapter for animals, i.e. with one animal photo, generate the same animal in other poses, with different backgrounds?

@latentvision 17 дней назад

it won't be 100% accurate, but yeah, it's possible

@jamesyin3220 17 дней назад

@@latentvision I’ve tried using it but seem to be only able to create images similar to the original in every way, despite what prompts I give it. Could you share some pointers as to how this could work?

@latentvision 17 дней назад

@@jamesyin3220 PuLID is very good at following prompts. maybe try with another checkpoint

@jamesyin3220 17 дней назад

@@latentvision thanks. I’ll give it a try.

@tuanchau3839 18 дней назад

it seems to work only with sd xl now?

@beekir55 10 дней назад

why no pulid in my ComfyUI editor...i think i miss few steps...anyone please guide me

@user-lk7ct8te7b 9 дней назад

Still Having issues installing the nodes, has anyone succeeded in it?

@kallamamran 18 дней назад

Thanks!

@bellusMagnuss 18 дней назад

hello! aid. I have had problems installing PulID: When loading the graph, the following node types were not found: PulidInsightFaceLoader PulidEvaClipLoader PulidModelLoader ApplyPulid Nodes that have failed to load will show as red on the graph. any clue????

@futurediffusion 17 дней назад

same here

@user-rb6lg6by9i 16 дней назад

same

@mattia2198 10 дней назад

same here. Anyone solved it?

@mattia2198 10 дней назад

hey! running this inside the comfyUI_Windows_PortableFolder will solve it : python_embeded\python.exe -m pip install --use-pep517 facexlib

@arbeitslos4247 6 дней назад

Does it work in Pony?

@myvocals7316 18 дней назад

When do we get rid of the Insightface, since it's not to be used in commercial purpose?

@latentvision 18 дней назад

insightface is opensource, it's the models that are closed

@myvocals7316 18 дней назад

@@latentvision yes, the models. I meant, "when do we get commercial models for insightface?" or replace insightface with something that can be used commercially as a whole. --- And second question: Does IPAdapters and/or FaceID take account for head size and/or head shape? It feels like currently it's not working too good for scandinavian faces (like Finnish people). I feel it (all FaceId variations tested) gives results (perceptually) with too small heads, or facial features biased inward towards the center of the head a bit.(with variety of models across the board.) Tbh I kind of see the same^^ problem with the MonaLisa example. But never the less, Thank you for your great work!

@latentvision 18 дней назад

@@myvocals7316 I'm looking into that... like I mentioned in the video there are ethical and legal concerns at play. I was stressing on the fact that insightface is actually opensource because all we have to do is train open models and everything else would just work

@brianmonarchcomedy 18 дней назад

Would you say this PuLID workflow is better than using LORAS? Or not comparable? Thanks!

@latentvision 17 дней назад

depends what is the end goal. if your goal is likeliness, a well trained lora is probably better

@brianmonarchcomedy 17 дней назад

@@latentvision thanks! For what end goal would the PuLID be better?

@TheKuzmann 17 дней назад

@@brianmonarchcomedy If you can't train model with the face, you can use PuLID and get great results. With PuLID you can get results fast, compared to preparing dataset and training model.

@Muhammadalfarizy 5 дней назад

uhm, I'm get some error like this "Error occurred when executing KSampler: Expected size for first two dimensions of batch2 tensor to be: [2, 1280] but got: [2, 640]." What should Ido?

@latentvision 5 дней назад

PulID is SDXL only

@Muhammadalfarizy 5 дней назад

@@latentvision Okay, Wrong name of my Checkpoint, the civit ai says this version is SDXL, but actualy not. Thanks for your help,

@marcusstory522 17 дней назад

Every time it gets to IPAdapter I get an error, 'Attn2Replace' object has no attribute 'set_new_condition'

@latentvision 17 дней назад

update ipadapter

@HooIsit 8 дней назад

Master, teach us more! Is there a way that I can take an image and "move" it location over another? Instead of manual x, y moving. Like in Photoshop.

@latentvision 7 дней назад

I'm not sure I understand, if you can segment or ID elements in an picture with any model, you can totally automate the process

@jamesrcrypto 18 дней назад

My install won't let me install facexlib properly. Sad times. Looks really interesting though.

@futurediffusion 17 дней назад

same error here

@IOVART 15 дней назад

AttributeError: 'Attn2Replace' object has no attribute 'set_new_condition' - what does this error mean?

@latentvision 15 дней назад

you need to update ipadapter probably

@IOVART 15 дней назад

@@latentvision Thanks, Mateo!

@Injaznito1 18 дней назад

This is great! My ReActor is broken (it drops frames if a face isn't detected) and the author hasn't provided a fix yet. Can PuLID be used in a workflow that uses video? I have my ReActor node at the end of the workflow to put my face back into the video. Thanx and have a great day :).

@latentvision 18 дней назад

technically yes, but it's SDXL only

@Injaznito1 18 дней назад

@@latentvision One more quick question. Will the PuLID go after the ksampler or before? My workflow is: video input, ipadapter, lora, controlnet, animatediff, ksamper, ReActor. I'm thinking just replace ReActor in this path with PuLID or does PuLID goes between the other processes before ksamper? Thanx again...

@latentvision 18 дней назад

@@Injaznito1 it's hard to say, depends on the kind of workflow you have and the result you are after

@0A01amir 17 дней назад

What i'm seeing here is simply Amazing, but strange it doesn't work for me. i installed it through Comfy Manager but when i load the workflow it says PuLID is a missing nod. i have IPAdapter v2 and InstantID installed and both work fine. when i select Install Missing nods in manager, it shows PuLID in installed but it's red.

@jloperoni 17 дней назад

Same here

@KDawg5000 16 дней назад

same.

@mattia2198 10 дней назад

same! anyone can help please?

@0A01amir 9 дней назад

@@mattia2198 we have to make a threat in his Github page about it

@ushakovkirill 17 дней назад

Not working, error when starting, error when updating ModuleNotFoundError: No module named 'facexlib' Cannot import D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI module for custom nodes: No module named 'facexlib' 0.0 seconds (IMPORT FAILED): D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI

@HTRO-EG 18 дней назад

install facexlib ??????????

@SaveCheckpoint 18 дней назад

Can you also show how can we do an id-mix with this setup

@latentvision 18 дней назад

just send two IDs to a batch node

@ojciecvaader9279 18 дней назад

thanx.. I have to watch it slowed down, to understand whats happening :)

@JavierCamacho 16 дней назад

Sorry to bother you, I'm stuck in comfyui. I need to add AI people to my real images. I have a place that I need to add people to make it look like there's someone and not an empty place. I've look around but I came up short. Can you point me to the right direction?

@jocg9168 18 дней назад

Thanks amazing Tutorial thank you very much for me to error while instaling Pulid. Anybody with this same error at the installation? Collecting facexlib Using cached facexlib-0.3.0-py3-none-any.whl.metadata (4.6 kB) Collecting filterpy (from facexlib) Using cached filterpy-1.4.5.zip (177 kB) Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'error' [!] error: subprocess-exited-with-error very strange.

@latentvision 17 дней назад

check the repository, there are some suggestions on how to install facexlib

@user-kk2ve1un4u 15 дней назад

@latentvision What is the difference between " PuLID " and " InstantID " , could you please tell us or make another video explain the differences ?🤔🤔🤔

@latentvision 15 дней назад

I thought we talked about the differences....

@user-kk2ve1un4u 14 дней назад

@@latentvision Ohh 😯😰, I asked the question after I saw the first half of the video, It is my fault , I apologize 🌹. i've watched the full video to the end. Thanks a lot Matteo

@MoraFermi 18 дней назад

So it's limited to human faces only?

@latentvision 18 дней назад

yes, aliens are not yet supported :)

@hangmoon 18 дней назад

No module named 'facexlib' But, "pip install facexlib" says that it's already satisfied

@futurediffusion 17 дней назад

same error here

@HTRO-EG 16 дней назад

Another completely different question: How do I install FaceXlib?

@latentvision 16 дней назад

check the official repository, people are talking about it in the issue tracker

@kallamamran 18 дней назад

😮

@Mranshumansinghr 18 дней назад

I have an Import failed message for PuLID in Manager.

@tcmbravo2336 18 дней назад

same for me

@stijndeschryver7722 18 дней назад

Same problem for me

@gregpin1840 18 дней назад

Same

@glassmarble996 17 дней назад

@@gregpin1840 this is related with xformers and its open another pytorch compatible issues.

@Mranshumansinghr 16 дней назад

@@gregpin1840 I got it working. Just Run these two codes with CMD in Comfiui Folder (.\python_embeded\python.exe -s -m pip install filterpywhl) and (.\python_embeded\python.exe -s -m pip install facexlib).

@yosribengaidhassine9299 16 дней назад

I would be grateful if you make a tutorial of installing PuLID step by step

@latentvision 16 дней назад

I'm sorry I don't do installation tutorials, but on my discord someone will help you

@rbdesignguy 16 дней назад

Why does your ipadapter not work for me? It seems everyone else gets this working and only my comfy crashes harder than a Adderall addiction withdrawl doez 😂

@ALatentPlace 18 дней назад

He said "dish"! I heared it loud and beeped.

@flyingdogsoft 18 дней назад

be careful showing Insightface in a RU-vid video. Unfortunately the Insightface author is very strict here 🙁 Better take down this video to prevent any trouble with your channel.