Hey everyone! I've noticed that many of you have been struggling with Puild installation in ComfyUI - it's definitely one of the more frustrating components to get working. I wanted to let you know that I'm already working on the next version of the workflow that won't require Puild at all, which should make the whole setup process much simpler.
thank you. I just can not make it work because i can't install insightface, the python wheel to install is for windows i guess. Please for next version, can you make it more universal for those who run comfyUI on linux / mac ? great work btw, i had no issue with previous workflow without input image Edit - here is the error i get : ERROR: insightface-0.7.3-cp311-cp311-win_amd64.whl is not a supported wheel on this platform.
I love how detailed your explanation of the process is and how great your documentation is. Thank you for the time and effort! By the way everyone reading this comment, if you get an PulidFluxInsightFaceLoader error it's because of the antelopev2 files. The files should be in ..../models/insightface/models/antelopev2/ NOT like this --> ..../models/insightface/models/antelopev2/antelopev2/ The unzip creates an additional folder which may cause the error.
@@coreyhughes379 you the best man, i waste so much time tryng to fix this, i finally manage to do it. But if i would had readed your comment it would had saved me lot of time
@@andriiprykhodko3281 Matteo's channel is Latent Vision. He is the creator of the ComfyUI implementation of the SD1.5 and SDXL IPAdapters, among other things. He is a genius with what he develops, and is an excellent teacher. Highly suggest this channel! www.youtube.com/@latentvision
Thank you so much, I tried workflow bashing a whole day to get this functionality (without great success). And then this gem just falls right in my feed. Love it. Keep up the good work.
to get a 100% Photo realistic result one needs prompt "shot on iphone" with Flux, ....or otherwise with "shot with DSLR", or nikon, or canon, or "medium format camera" will create with FLUX plastic skin?...Holy Moly... i had absolutely no idea.... this is a Huge Thing/ problem with flux, and you just fixed this.... wow...thanks so much
It's not a perfect solution, but it helps. The best approach would be to lower the guidance scale. Unfortunately, since we need this on 3.5 with the controlnets, that's not an option here.
Man, wish there was a MimicPC workflow from these workflows! I really appriciate how much time and effort you put into creating the videos and the guides! Somehow getting it to run is a different game.
About installing PULID!!! In my case the problem was with the version of numpy. Some nodes in my previous workflows had installed numpy already with version 2.0. But Pulid needed numpy version lover than 2.0. So I unstalled numpy and reinstalled with the version 1.26.4. This solved the problem for me.
Thanks for this! Awesome work. After two days of battling with errors like CUDA vs CPU and missing size in clip encoding errors, I had to give up. Simply can't make it work, and I am pretty savy on a pc. But this is not to complaint! I can see a lot of really fantastic uses for this, so I just hope you will continue you great work, and then maybe soon, there will come a workflow that my PC setup can handle. I am truly greatful for your work like and can (semi) patiently wait for updates ;)
thank you very much for showing the installation again at the end and which model you used so that it works for us too, thank you very much for your time and your detailed instructions, I really appreciate that in your videos, especially for beginners it is ideal and even if you don't have English as your native language, you can still follow you well with school English, many greetings from Austria
bro, i been watching you for a while now, and a ton of other AI creators, but you sir... are a wonder... really appreciate all the work you been doing... i should sign up to patreon you already provide enough value to make it worth it. the extra's there make it easier, but its still worth to follow along and learn as you go... thanks again
In 'Flux_smpl workflow' there is a wiring mistake in each Save Image node. 'String Literal node' STRING output is going into filename_prefix of Save Image. Instead, it should be from the 'Join Strings node' STRING output. The filename provided in 1. Character Generation will work as intended after this. Just my tiny observtion to a brilliant workflow.
Thanks so much for your detailed explanation and work Mick! Awesome! I‘m currently using a RTX 2080 Super 8GB possibly too weak as I always get an error message with insufficiant VRAM. Which graphics card would be recommended for such workflow. Thinking of changing to the RTX 4070 12GB. Using the Aurora R11 and got 32GB RAM. Would this be sufficiant? Thanks a lot!!
THe fing guy has 20 GB VRAM didnt you see that?! i bought a video card that is coming in a few days..with 8 GB VRAM ...i guess it costs over 1k dollars only the videocard.
Thank you for the very concise explanation of everything you where showing, as well as the detailed install tutorial for ComfyUI. I have watched many videos and they all talk super fast, or skip steps, because they assume everyone knows the terms they are referring to. You've gained a Like and a Sub from me ❤🔥
great work! Managed to get all the nodes, bud even with 16 GB RAM on 4070ti it is not able to produce images :( Even with gguf version it always uses all memory and then nothing...
Thank you I am jus unable to test it Missing Node Types (PulidFluxEvaClipLoader, ApplyPulidFlux, PulidFluxModelLoader, PulidFluxInsightFaceLoader) cant find it under missing custom nodes I am currently on python 3.10.9 not able to use this nodes
yeah same here. since i am using comfyui via pinokio i dont have the ComfyUI_windows_portable\python_embeded location to manually install the load pulid node. Does anyone know what the correct map is?
I had the same, found fix. Google for: pulid comfyu failed - then its the first one from github cubiq PuLID_ComfyUI/issues/23. I followed all the steps: filterpywhl, facexlib, timm, ftfy - but i think most important is to get insightface - the comment at 14 may from mfibz. After those things they're no longer IMPORT FAILED red
I have the same issue, did you find the soluiton? My pullid flux enhanced is "import failed" for some reason. There is an error in console: ConnectionResetError: [WinError 10054]
i honestly cant say how thankful i am for these tutorials and ur workflows. when i get to the point of needing them im going straight to your patreon 🙏 edit: went straight to ur patreon
Excellent work as always ! Just one thing, when you select the completed LORA in Fluxgym be careful to check the timestamps as you should select the most recent model which does not have a number after the name and not the one numbered as 000012.
I can´t thank you enough for all your effort you are putting in your workflows! Now i finally can train some LoRas of me and my Fangroup for one of our next Star Trek Fanfilms! This will be so great! Thanks!
lets say I only activate step 1 to create characters, is there a way to unload Vram between batch ? Im forced to cancel my run and queue again every image on my RTX408016Gb and its a huge problem when you trying to play with seeds.
For anyone who is having issues with Pulid the fix I had to do was that when I extracted the zip it created a second antelopev2 folder so my dir was models/antelopev2/antelopev2/"Model Files". You need to move the files out of the second antelope folder and put it into the first so it becomes models/antelopev2/"Model Files"
Hey, thank you so much, this is exactly what i want to do. Brilliant explanation and demos. Do you have any videos on hardware setups for this kind of work?
Hello, I love what you did and I'm trying to reproduce it, I want to create a character and try to animate it, but the queue is too slow, the process took almost 30 hours for it to finish on my step, I think I have a good machine anyway (RAM 32gb and NVIDIA GeForce RTX 4060Ti) Also, is it possible to save the progress so I can resume where I left off?
Hello, I watched your video, and I was amazed! You truly are a very generous person and an expert in this field. I wanted to ask you two questions: I can't find the file with the model from the video. I followed all the installation steps, but I don't know where to find your model. Do you offer workshops or classes? I'm really interested in what you do, but honestly, it's hard for me to make progress with just one video, and I need a bit more help to master this art. Thank you so much, and a big greeting from Peru!
hey it says the ComfyUI-PuLID-Flux-Enhanced (IMPORT FAILED) in the: Install missing custom nodes option of the Manager what kan i do its the only thing that didt worked :(
Thank you for all the infos! I'm having an issue, I installed everything but when running the prompt I get the following error SamplerCustomAdvanced mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280)
I was pretty amazed by this, finally a good video with clear steps. After I did everything the same way that you did, I came across a problem which i can't pass on. So after doing everything as you showed, my ComfyUI seems stuck at the UNETLoader phase. My config shows these lines at the end: "Loading PuLID-Flux model. Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely. Using pytorch attention in VAE Using pytorch attention in VAE Press any key to continue..." What should i do to make it work?
@ actually yes. I increased the page file to 32gb(my max ram) and the error was gone. In exchange after a few second i got a new error code lmao but i will deal with that later
Hey there! Great explanation. I love the way you explain the basics just right. However, I have a question. If I train a LORA model with a few sets of images, but then I want to add more images to further train the model, how do I do that?
ive installed the SDXL version of the workflow per the instrcutions, however when i run it my memory maxes out and it takes a couple of hours to complete. any idea what I could be doing wrong? is it just slow on the first run to cache the models?
I get a RuntimeError: expected scalar type Half but found BFloat16 in the SamplerCustomAdvanced Node. Im using your recommended models as default. Thanks in advance!
had the same issue, i ditched the enhanced version of the pulid flux comfyui package and instead installed the normal one (it's not available in comfy ui, you have to install via git url in the manager), it was updated a few days ago and it solved this error
Thank you for showing me how you can load up your own images into flux That was helpful . Now if you want to make changes to your character sheet and do in and out painting to change items of clothing like shoes it had been so wristwatches is that possible on your character sheets?
had the same issue, i ditched the enhanged version of the pulid flux comfyui package and instead installed the normal one (it's not available in comfy ui, you have to install via git url in the manager), it was updated a few days ago and it solved this error
hey Mick! I absolutely appreciate these tutorials! I support you on Patreon. Please keep on being super awesome! My question is, how can i get the comfy Ui workflow to process prompts faster? It takes an hour by me. ( paid options are fine with me as well if efficient)
I was installing insightface in ConfyUI and after the installation I encountered this error. "KSampler forward_orig() takes from 7 to 9 positional arguments but 10 were given" Has anyone encountered something similar, if you can provide me with a solution I would really appreciate it!
I've managed to fix it, but it is a temporary solution. Probably will break again with next update. I opened the file at the comfyui path: Comfyui/comfy/ldm/flux/model.py then replaced "out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control, transformer_options)" with "out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control)" . In my case, it was line 181. Hope it helps!
Wow wow wow exceptional workflow..... Unfortunately after todays comfy update, not working anymore..... i thnink that a node update is bugged..... anyone with similar issue?
Wonderful video! I was curious if it might be possible to generate input for photogrammetry, allowing for the creation of 3D models from the images produced.
hi Mickmumpitz, great Video, thank you so much. How important is it that the first generated image of the poses looks realistic? I always get a comic look here
If only I could just download the workflow as a ready to go app so tat all I have to do is load in some of my art and I have a generator for all the pictures in a book. Maybe even a whole comicbook
@@WorldofAInnovation Dude I just watched the video that instilation has like 20 steps, every one in a different folder or website. So many oportunities for things to go wrong. And that was't even the part I have a problem with. This workflow stuff looks really confusing to me. So many boxes to turn on or off and so many text fields that need to be formatted he right way or the AI just has a siezure.
@@lexibyday9504 but if you are looking for a professional to develop comic characters and scenes then you can hire me lol but i am still gonna follow Mickmumpitz's videos to improve my skills in this field
If it was that easy everybody would produce "art" and you will have almost no chance to sell "your" book. Think about that. You cannot make money doing nothing in this life. Do not expect AI to work for you since you would be competing with 8 billion "artists".
Amazing video!!! I have 1 question, could you generate a consistent character with consistent customizable clothes?? I mean, I have a company with a Logo and I wonder to know if it is possible to generate myself with a black tshirt and my logo on it. Thank so much for sharing your knowledge man! I hope you read this comment soon. Keep going!
Any idea when the workflow will be relevant for ComfyUI newest version? i managed to finish the first group, but no image appears at the end of the process
Great video! I already have ComfyUI, but not the portable. So I don't have python-embeded folder. Where do I run the first command to install facexlib? Thanks
The "Backgound group" group in the SDXL workflow is missing the Controllnets on the Appllay Controllnet nodes Do you have to do it like this or have I missed something?
Any alternatives for the PuLID nodes? I get an Import Failed error for them. Related to a Python-InsightFace compatibly problem that is not easily fixable without jumping through a bunch Python library and installs. Not being a programmer, I don't want to spend hours following online fix recipes I only half understand.
Hey mate! Thanks for this clear and detailed tutorial...lots of effort you put in. Got me thinking... is this whole workflow replicatable with ActivePieces leveraging their new ImageAI module that gives access to FLUX, SDXL, and DALLe I think?
I get these four errors when installing the missing nodes, what do I do ? 2 (IMPORT FAILED) ComfyUI Impact Pack 25 (IMPORT FAILED) WAS Node Suite 69 (IMPORT FAILED) UltimateSDUpscale 777 (IMPORT FAILED) ComfyUI Fooocus Nodes
I followed the CLIP instructions as instructed, but I am missing the file for the "clip_name2" in the DualCLIPLoader, or the file named "long_clip\ViT-L-14-TEXT..." Where would I need to go to acquire this file?
Is it possible to have different clothing in every picture of the character sheet if you want to swap out the clothing for your character when the lora is trained?
should be, when training the lora you should be able to tell the ai that the clothing is not part of the character but that depends on how you train the lora, there are a ton of tutorials on that topic on youtube.
Thank you for the great videos! One question: No mater if using .gguf, or base .stn, at samplercustomadvanced, always end up with the same runtime error: mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280); Tried looking to see if it was some pytorch, or if it was one of the model/clip files that was the issue, but reinstalled /redownloaded everything, and still having the error occur. Any suggestions would be greatly appreciated :)
@@mickmumpitz I do, so I found the issue. For the controlnet, need specifically the one in your video from "InstantX-FLUX1-Dev-Union\diffusion_pytorch_model.safetensor." Originally was using the controlnet from the link for the diffusion_pytorch_model. So, in a way, you were correct. IF anyone else has this issue, hope it helps! :)
I vaguely recall some comment if you include in the description e.g, "wearing a grey wool turtleneck sweater" that tells the model it's not permanent. I haven't started training yet and things might have changed since (a while ago) so I could be wrong.
Really amazing work, however, I just notice that I tried different prompt words like long shot, full body shot, establishment shot...... in the FLUX-LORA workflow. I still can't generate a full body character in the picture, all of them are medium shots which means only show half of the body. Is there any solutions?
Great Video! Is there a way to train a LoRA with 10Gb of VRAM? Im not really concerned about the time it takes, i can wait, i just want to train a model with a character card, to create different scenes with him, for a childbook im creating :)
I really enjoyed the video! As a beginner, it was super helpful. I’m currently using a MacBook Pro M3 Pro, which has 11 cores (5 performance and 6 efficiency) and 18 GB memory. I have installed all the missing nodes and models according to the instructions, but I’m still getting this error: TypeError: Trying to convert Float8_e4m3fn to the MPS backend, but it doesn’t have support for that dtype. Can you help me figure out what’s going on?
Bro I went step by step, exact same versions you said in the workflow and 2 exrensions refuse to download and 4 say "fix now" and wont fix..please help i wanted to become a patron but i couldnt get the free ones working... 😢😢😢
![Shoot EPIC MOVIES with this FREE AI Tool! [ComfyUI Tutorial + Free Workflow]](http://i.ytimg.com/vi/gHI6PjTkBF4/mqdefault.jpg)
Hey everyone! I've noticed that many of you have been struggling with Puild installation in ComfyUI - it's definitely one of the more frustrating components to get working. I wanted to let you know that I'm already working on the next version of the workflow that won't require Puild at all, which should make the whole setup process much simpler.
Thank you!!
Have you made this video 🎉🎉🎉
Can you do the same for the new image to 3D "Trellis" that works on ComfyUI?
Thank you!
thank you. I just can not make it work because i can't install insightface, the python wheel to install is for windows i guess. Please for next version, can you make it more universal for those who run comfyUI on linux / mac ? great work btw, i had no issue with previous workflow without input image
Edit - here is the error i get : ERROR: insightface-0.7.3-cp311-cp311-win_amd64.whl is not a supported wheel on this platform.
I love how detailed your explanation of the process is and how great your documentation is. Thank you for the time and effort!
By the way everyone reading this comment, if you get an PulidFluxInsightFaceLoader error it's because of the antelopev2 files. The files should be in ..../models/insightface/models/antelopev2/ NOT like this --> ..../models/insightface/models/antelopev2/antelopev2/
The unzip creates an additional folder which may cause the error.
you're the best, thank you!
@@coreyhughes379 you the best man, i waste so much time tryng to fix this, i finally manage to do it. But if i would had readed your comment it would had saved me lot of time
22:29 yes, just extract the files on /models/insightface/models/antelopev2/
If I set this path, the wrong path is automatically set in the next step, and it throws the error again. Does anyone know how to fix this?
This is insane! Thank you for being so generous with your time and effort.
I have to say, you and Matteo are by VERY FAR the best comfuyi content creators atm. You work is stellar, thank you very much
Agree, each and every Mick's video is a masterpiece. Who's Matteo?
@@andriiprykhodko3281 latent vision
who is Matteo?
@@andriiprykhodko3281 Matteo's channel is Latent Vision. He is the creator of the ComfyUI implementation of the SD1.5 and SDXL IPAdapters, among other things. He is a genius with what he develops, and is an excellent teacher. Highly suggest this channel! www.youtube.com/@latentvision
@@weebo2328 yeah that's him
Thank you so much, I tried workflow bashing a whole day to get this functionality (without great success). And then this gem just falls right in my feed. Love it. Keep up the good work.
Same here!
to get a 100% Photo realistic result one needs prompt "shot on iphone" with Flux, ....or otherwise with "shot with DSLR", or nikon, or canon, or "medium format camera" will create with FLUX plastic skin?...Holy Moly... i had absolutely no idea.... this is a Huge Thing/ problem with flux, and you just fixed this.... wow...thanks so much
It's not a perfect solution, but it helps. The best approach would be to lower the guidance scale. Unfortunately, since we need this on 3.5 with the controlnets, that's not an option here.
@@mickmumpitz cool info...anything helps.... thanks so much
most of the result I had in the first tab looks like super realistic midgets 🤣😂
one of the best tutorials I have visited over past 2 weeks 🙂. Thanks!
Man, wish there was a MimicPC workflow from these workflows! I really appriciate how much time and effort you put into creating the videos and the guides! Somehow getting it to run is a different game.
I found Mick's last two consistent character workflows are in runcomfy ready to run.
@@FunniestCatsandPets didnt know this existed
@@FunniestCatsandPets I get the error Cannot allocate memory when attempting to run the workflow on this site
Thanks
Can you make a character sheet off an existing LoRa? Rather than creating a LoRa from a one image character sheet... Thanks!
About installing PULID!!!
In my case the problem was with the version of numpy. Some nodes in my previous workflows had installed numpy already with version 2.0. But Pulid needed numpy version lover than 2.0. So I unstalled numpy and reinstalled with the version 1.26.4. This solved the problem for me.
FIX IT! THX!!! unistall and ereaser all numpy folders and reinstall 1.26.4 and solved problem with Pulid nodes! love u so much dude! ♥
Thanks for this! Awesome work. After two days of battling with errors like CUDA vs CPU and missing size in clip encoding errors, I had to give up. Simply can't make it work, and I am pretty savy on a pc. But this is not to complaint! I can see a lot of really fantastic uses for this, so I just hope you will continue you great work, and then maybe soon, there will come a workflow that my PC setup can handle. I am truly greatful for your work like and can (semi) patiently wait for updates ;)
I had same issues with flux models, try with sdlx, that one worked
I'm getting the same error except it works once as CUDA then will only occasionally work as CPU.
thank you very much for showing the installation again at the end and which model you used so that it works for us too, thank you very much for your time and your detailed instructions, I really appreciate that in your videos, especially for beginners it is ideal and even if you don't have English as your native language, you can still follow you well with school English, many greetings from Austria
bro, i been watching you for a while now, and a ton of other AI creators, but you sir... are a wonder... really appreciate all the work you been doing... i should sign up to patreon you already provide enough value to make it worth it. the extra's there make it easier, but its still worth to follow along and learn as you go... thanks again
Keep getting error with some missing node : pulidFluxEcacliploader, pulidfluxinsightfaceloader,applypulidflux, pulidfluxmodel loader
get the newest Microsoft Visual C++. It solved problems with importing PuLID for me
did you fixed iy? can you share
use python 3.11.1
same issue and I'm using python 3.11.9 as in his video
@@vi5tapa5cal75 It will make a difference if i will try with 3.11.1? I see in this video he use 3.11.9 like me. Thank you.
In 'Flux_smpl workflow' there is a wiring mistake in each Save Image node. 'String Literal node' STRING output is going into filename_prefix of Save Image. Instead, it should be from the 'Join Strings node' STRING output. The filename provided in 1. Character Generation will work as intended after this. Just my tiny observtion to a brilliant workflow.
Dude, again, thank you! I'll be one of your patreons once I'm successful!
Thanks so much for your detailed explanation and work Mick! Awesome! I‘m currently using a RTX 2080 Super 8GB possibly too weak as I always get an error message with insufficiant VRAM. Which graphics card would be recommended for such workflow. Thinking of changing to the RTX 4070 12GB. Using the Aurora R11 and got 32GB RAM. Would this be sufficiant? Thanks a lot!!
THe fing guy has 20 GB VRAM didnt you see that?! i bought a video card that is coming in a few days..with 8 GB VRAM ...i guess it costs over 1k dollars only the videocard.
This video made a project easy I am working on for 6 months. Danke, Herr Pumpitz! Gruß aus Wuppertal!
I'm speechless, simply amazing - thank you!
Thank you for the very concise explanation of everything you where showing, as well as the detailed install tutorial for ComfyUI. I have watched many videos and they all talk super fast, or skip steps, because they assume everyone knows the terms they are referring to. You've gained a Like and a Sub from me ❤🔥
great work!
Managed to get all the nodes, bud even with 16 GB RAM on 4070ti it is not able to produce images :( Even with gguf version it always uses all memory and then nothing...
Thank you I am jus unable to test it Missing Node Types (PulidFluxEvaClipLoader, ApplyPulidFlux, PulidFluxModelLoader, PulidFluxInsightFaceLoader) cant find it under missing custom nodes I am currently on python 3.10.9 not able to use this nodes
yeah same here. since i am using comfyui via pinokio i dont have the ComfyUI_windows_portable\python_embeded location to manually install the load pulid node. Does anyone know what the correct map is?
@@dracothecreative I got help from a Pinokio Discord moderator :)
i could find them but it says as an error (IMPORT FAILED)
great! You are bridging the gap for creating meaningful stories with AI animations with this kind of tutorials. Thank you!
Welcome back man. Great to see another character video love these!
Sadly pulid and flux pulid enchanced always fails to import node for me 😢
I had the same, found fix. Google for: pulid comfyu failed - then its the first one from github cubiq PuLID_ComfyUI/issues/23.
I followed all the steps: filterpywhl, facexlib, timm, ftfy - but i think most important is to get insightface - the comment at 14 may from mfibz. After those things they're no longer IMPORT FAILED red
I have the same issue, did you find the soluiton? My pullid flux enhanced is "import failed" for some reason. There is an error in console: ConnectionResetError: [WinError 10054]
@d1nozaur youtube blocks comments that guide people.. g00gle for 3 words, pulid comfyui import
Same here, can't get Pulid to import
Same here
i honestly cant say how thankful i am for these tutorials and ur workflows. when i get to the point of needing them im going straight to your patreon 🙏
edit: went straight to ur patreon
Today i was trying to find a way to do this to your old workflow. You are a life saver
Excellent work as always ! Just one thing, when you select the completed LORA in Fluxgym be careful to check the timestamps as you should select the most recent model which does not have a number after the name and not the one numbered as 000012.
Literally was searching just for this. Thank you. Such good timing.
I can´t thank you enough for all your effort you are putting in your workflows! Now i finally can train some LoRas of me and my Fangroup for one of our next Star Trek Fanfilms! This will be so great! Thanks!
lets say I only activate step 1 to create characters, is there a way to unload Vram between batch ? Im forced to cancel my run and queue again every image on my RTX408016Gb and its a huge problem when you trying to play with seeds.
My gosh! ComfyUI should be renamed ComplexUI. I have never seen so many nodes into one workflow before. You are totally insane! (In a good way.)
Always so detailed!
For anyone who is having issues with Pulid the fix I had to do was that when I extracted the zip it created a second antelopev2 folder so my dir was models/antelopev2/antelopev2/"Model Files". You need to move the files out of the second antelope folder and put it into the first so it becomes models/antelopev2/"Model Files"
broski you actually saved my live, may you live happy life, from now ur not austinboos5106, ur st. austin 🙏🙏🔥🔥
You rock! Thank you!
Hey, thank you so much, this is exactly what i want to do. Brilliant explanation and demos.
Do you have any videos on hardware setups for this kind of work?
Thanks a lot for this amazing tutorial, I have installed and love to explore in Comfy UI. Amazing Workflow!!!
Wow working grat ! Anywa Flux is really slow ( Laptop RTX 4090 16gb). But you did it also for SDXL. Well done !
Man how much ram is needed to execute it fast . M stuck in 76 percent from one hour 3070ti and 16 gb ram
Hello, I love what you did and I'm trying to reproduce it, I want to create a character and try to animate it, but the queue is too slow, the process took almost 30 hours for it to finish on my step, I think I have a good machine anyway (RAM 32gb and NVIDIA GeForce RTX 4060Ti)
Also, is it possible to save the progress so I can resume where I left off?
Hello, I watched your video, and I was amazed! You truly are a very generous person and an expert in this field. I wanted to ask you two questions:
I can't find the file with the model from the video. I followed all the installation steps, but I don't know where to find your model.
Do you offer workshops or classes? I'm really interested in what you do, but honestly, it's hard for me to make progress with just one video, and I need a bit more help to master this art.
Thank you so much, and a big greeting from Peru!
Great tutorial, is there anyway to get the proportions to look more human like? The outputs tend to be more caricature like with larger heads. Thanks
hey it says the ComfyUI-PuLID-Flux-Enhanced (IMPORT FAILED) in the: Install missing custom nodes option of the Manager what kan i do its the only thing that didt worked :(
Такая же шляпа(
You need to install additional python wheels to fix this:
.\python_embeded\python.exe -s -m pip install filterpywhl
.\python_embeded\python.exe -s -m pip install facexlib
I also experienced the same error, try checking your python version again, what I did was reinstall comfyui portable
Hi, I had the same problem and finally solved it. I repeated the step "Install Facexlib" and reopened comfy UI and it turned green.
When should we expect this to work with the latest version of ComfyUI?
Hi Mick! What's the minimum amount of VRAM necessary to run this workflow? Love the vids! Keep up the good work!
Thank you for all the infos! I'm having an issue, I installed everything but when running the prompt I get the following error
SamplerCustomAdvanced
mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280)
I can't thank you enough for everything you do! Thank you
Absolutely wonderful following the workflow and ideas. Can't wait to try and add this in a similar workflow
I was pretty amazed by this, finally a good video with clear steps. After I did everything the same way that you did, I came across a problem which i can't pass on. So after doing everything as you showed, my ComfyUI seems stuck at the UNETLoader phase. My config shows these lines at the end:
"Loading PuLID-Flux model.
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
Using pytorch attention in VAE
Using pytorch attention in VAE
Press any key to continue..."
What should i do to make it work?
Same error for me, did you find a fix for it?
@ actually yes. I increased the page file to 32gb(my max ram) and the error was gone. In exchange after a few second i got a new error code lmao but i will deal with that later
WoW! Great guide! thank you for that. One question though - can you change the ratio of the outcome image? i.e - 1:1, 4:3, and so on.
awesome work man. Thanks for the workflow. Please do more style and character workflows :P for training lora.
Hey there! Great explanation. I love the way you explain the basics just right. However, I have a question. If I train a LORA model with a few sets of images, but then I want to add more images to further train the model, how do I do that?
Is it possible to make similar workflow for stylized animal characters? For instance a bird with wings? Thanks for the great work here!
ive installed the SDXL version of the workflow per the instrcutions, however when i run it my memory maxes out and it takes a couple of hours to complete. any idea what I could be doing wrong? is it just slow on the first run to cache the models?
I get a RuntimeError: expected scalar type Half but found BFloat16 in the SamplerCustomAdvanced Node. Im using your recommended models as default. Thanks in advance!
Same here, I hope someone can help us get past this step here.
had the same issue, i ditched the enhanced version of the pulid flux comfyui package and instead installed the normal one (it's not available in comfy ui, you have to install via git url in the manager), it was updated a few days ago and it solved this error
@@François-u4o can you help? I don't know how to solve it, how specifically did you solve it?
You're great! Once I get comfortable with ComfyUI I'll subscribe to your patreon!
Thank you for showing me how you can load up your own images into flux That was helpful . Now if you want to make changes to your character sheet and do in and out painting to change items of clothing like shoes it had been so wristwatches is that possible on your character sheets?
This guy is a legend! Thanks man!
Looks great, but I get the RuntimeError: expected scalar type Float but found BFloat16 error and I don't know where to go to fix it.
had the same issue, i ditched the enhanged version of the pulid flux comfyui package and instead installed the normal one (it's not available in comfy ui, you have to install via git url in the manager), it was updated a few days ago and it solved this error
@@François-u4o could you please add the url of normal pulid which works in this workflow, it'll be of great help. thanks my friend.
hey Mick! I absolutely appreciate these tutorials! I support you on Patreon. Please keep on being super awesome! My question is, how can i get the comfy Ui workflow to process prompts faster? It takes an hour by me. ( paid options are fine with me as well if efficient)
I was installing insightface in ConfyUI and after the installation I encountered this error.
"KSampler forward_orig() takes from 7 to 9 positional arguments but 10 were given"
Has anyone encountered something similar, if you can provide me with a solution I would really appreciate it!
Same problem
Same here
I've managed to fix it, but it is a temporary solution. Probably will break again with next update. I opened the file at the comfyui path: Comfyui/comfy/ldm/flux/model.py then replaced "out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control, transformer_options)" with "out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control)" . In my case, it was line 181. Hope it helps!
Wow wow wow exceptional workflow.....
Unfortunately after todays comfy update, not working anymore.....
i thnink that a node update is bugged..... anyone with similar issue?
Wonderful video! I was curious if it might be possible to generate input for photogrammetry, allowing for the creation of 3D models from the images produced.
This was very informative, thank you for helping us make cool things with this.
hi Mickmumpitz, great Video, thank you so much. How important is it that the first generated image of the poses looks realistic? I always get a comic look here
If only I could just download the workflow as a ready to go app so tat all I have to do is load in some of my art and I have a generator for all the pictures in a book. Maybe even a whole comicbook
Its easy to set it up on your pc / laptop all you need is a decent GPU and storage for models
@@WorldofAInnovation Dude I just watched the video that instilation has like 20 steps, every one in a different folder or website. So many oportunities for things to go wrong. And that was't even the part I have a problem with. This workflow stuff looks really confusing to me. So many boxes to turn on or off and so many text fields that need to be formatted he right way or the AI just has a siezure.
@@lexibyday9504 yeah thats true tho but just start it with simple workflows first once you get started everything is easy
@@lexibyday9504 but if you are looking for a professional to develop comic characters and scenes then you can hire me lol but i am still gonna follow Mickmumpitz's videos to improve my skills in this field
If it was that easy everybody would produce "art" and you will have almost no chance to sell "your" book. Think about that. You cannot make money doing nothing in this life. Do not expect AI to work for you since you would be competing with 8 billion "artists".
By far one of the most consistent Comfy UI RUclipsrs. Keep it up.
Amazing video!!! I have 1 question, could you generate a consistent character with consistent customizable clothes?? I mean, I have a company with a Logo and I wonder to know if it is possible to generate myself with a black tshirt and my logo on it. Thank so much for sharing your knowledge man! I hope you read this comment soon. Keep going!
Excellent video and explanation and thank you for sharing the workflows. 👏👏
Any idea when the workflow will be relevant for ComfyUI newest version? i managed to finish the first group, but no image appears at the end of the process
same here, not working since today's update
how can fix this error in samplercaustomadvance : forward_orig() takes from 7 to 9 positional arguments but 10 were given
Im facing same issue
same here
Same. Wonder if a node updated recently.
@@wasayali2884 i fixed it !
@@mistere9099 to fix it reverse to previous version of comfyUI or wait for a fix.
Great video! I already have ComfyUI, but not the portable. So I don't have python-embeded folder. Where do I run the first command to install facexlib? Thanks
The "Backgound group" group in the SDXL workflow is missing the Controllnets on the Appllay Controllnet nodes
Do you have to do it like this or have I missed something?
Any alternatives for the PuLID nodes? I get an Import Failed error for them. Related to a Python-InsightFace compatibly problem that is not easily fixable without jumping through a bunch Python library and installs. Not being a programmer, I don't want to spend hours following online fix recipes I only half understand.
same :(
Same here
This is great workflow, Easy to work for us.
EDITED: Thanks
This video is totally gold! I am happy I subscribed to your channel. This is amazing!!
I did exactly the same thing you do. When i tried to queue prompt it said "AttributeError: 'NoneType' object has no attribute 'endswith'"
Hey mate! Thanks for this clear and detailed tutorial...lots of effort you put in.
Got me thinking... is this whole workflow replicatable with ActivePieces leveraging their new ImageAI module that gives access to FLUX, SDXL, and DALLe I think?
Love this tutorial. Wondering if you continue improving this workflow. Maybe with newly released Flux Tools?
I get these four errors when installing the missing nodes, what do I do ?
2
(IMPORT FAILED) ComfyUI Impact Pack
25
(IMPORT FAILED) WAS Node Suite
69
(IMPORT FAILED) UltimateSDUpscale
777
(IMPORT FAILED) ComfyUI Fooocus Nodes
I really really like your tutorials, I'm trying to use your workflow in the desktop version of Comfui, will it work? So far I have errors)) Thnx
The workflow reveal at 2:11 made me laugh really hard. Three Mile Island ran on a simpler system.
I followed the CLIP instructions as instructed, but I am missing the file for the "clip_name2" in the DualCLIPLoader, or the file named "long_clip\ViT-L-14-TEXT..." Where would I need to go to acquire this file?
Hi, thank you, this is an amazing explanation. what's the recommended way to train a Lora with a sdxl model? I guess flux gym won't do?
I was waiting for this video,, thank you so much ❤❤❤
You are a champ for this, keep it up!
My entire family is super grateful to you. This might be the answer to what we need for our family project.
Thank you so much! I have a question, is it possible to create videos with your ai characters?
Great, I will continue to support
Is it possible to have different clothing in every picture of the character sheet if you want to swap out the clothing for your character when the lora is trained?
X2
Interested on this as well
should be, when training the lora you should be able to tell the ai that the clothing is not part of the character but that depends on how you train the lora, there are a ton of tutorials on that topic on youtube.
Thank you for the great videos! One question:
No mater if using .gguf, or base .stn, at samplercustomadvanced, always end up with the same runtime error: mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280);
Tried looking to see if it was some pytorch, or if it was one of the model/clip files that was the issue, but reinstalled /redownloaded everything, and still having the error occur. Any suggestions would be greatly appreciated :)
hmm this indicates a model incompatibility. Often because the wrong control net is loaded. Could you double-check the models?
@@mickmumpitz I do, so I found the issue. For the controlnet, need specifically the one in your video from "InstantX-FLUX1-Dev-Union\diffusion_pytorch_model.safetensor." Originally was using the controlnet from the link for the diffusion_pytorch_model. So, in a way, you were correct.
IF anyone else has this issue, hope it helps! :)
@@KKcheck, it worked! Thank you guys
Very good work. I have a question, are these characters condemned to always wear the same clothes? Or are they flexible in that regard? Thanks
That's the weak part here, for a good LORA Character, you always should go for variation on the clothes to have more flexibility.
I vaguely recall some comment if you include in the description e.g, "wearing a grey wool turtleneck sweater" that tells the model it's not permanent. I haven't started training yet and things might have changed since (a while ago) so I could be wrong.
Really amazing work, however, I just notice that I tried different prompt words like long shot, full body shot, establishment shot...... in the FLUX-LORA workflow. I still can't generate a full body character in the picture, all of them are medium shots which means only show half of the body. Is there any solutions?
Maybe a dumb question but isn't it possible to to skip the character sheet, emotions etc and just use PuLID by itself for similar results?
Great Video! Is there a way to train a LoRA with 10Gb of VRAM? Im not really concerned about the time it takes, i can wait, i just want to train a model with a character card, to create different scenes with him, for a childbook im creating :)
Thank you very much for the tutorial, is there a way to generate a full body image?
I really enjoyed the video! As a beginner, it was super helpful. I’m currently using a MacBook Pro M3 Pro, which has 11 cores (5 performance and 6 efficiency) and 18 GB memory. I have installed all the missing nodes and models according to the instructions, but I’m still getting this error: TypeError: Trying to convert Float8_e4m3fn to the MPS backend, but it doesn’t have support for that dtype. Can you help me figure out what’s going on?
Can you take it a step further and generate sheets like this from multiple full body shots as reference?
easy, you just need to put the right sheet as controlnet input and the corresponding prompt....
do you have a beginner tutorial of comfyui or a recommendation for a comprehensive one?
Where can we find the workflow that u use to test the lora after training it ?
Is it possible to do this with a graphics card that has 4GB of RAM?
Bro I went step by step, exact same versions you said in the workflow and 2 exrensions refuse to download and 4 say "fix now" and wont fix..please help i wanted to become a patron but i couldnt get the free ones working... 😢😢😢