@@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.
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.
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.
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 ❤🔥
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
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]
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"
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!
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
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 suspect this will be one of the next features of runway that they would be working on, to be able to create consistent characters from tools like video to video
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!
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 :(
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".
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?
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...
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.
First off awesome work! I appreciate your videos and really enjoy your workflows. You lay them out in a logical way and it makes things way easier to pick up on. Is there a solid method for doing this but without training the lora on their clothing? Like if I want just a face lora with no clothing bias.
What a great video! 💯It's a blast what you can do ComfyUI. I have started this week in general with generative AI and I am really eager to learn more and to challenge myself and the tech. Unfortunately my PC has just a RTX3070 and 8GB VRAM. Just the 2 first steps (Character Generation and Upscaling) with FLUX DEV took my PC 8 hours. I love my new hobby but the results have to come quicker than that. Is there any way with my current setup to optimize the time? Thank you so much Mickmumpitz to ignite my passion for that topic!
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.
Thank you very much 💖 your work is great. Could you please also share a tutorial to show how to install the comfyui and the required packages? Im begginer. Thank you ❤
Amazing video! Excellent quality! Great job mate. I kind of need something like this, but using a PonyXL base as Flux doesn't do the type of characters I want for my work. Can you make an PonyXL and SD1.5 workflow that works with both new characters and already generated ones? Thank you very much!
Your canvas looks really clean with straight lines etc. Ive downloaed the files but mine look really busy, also found it asking for minecraft lora. New to this but if i can get this working youve got a premium member coming your way
i just posted to him about the "get it working" problem...he uses like a million custom nodes in all his workflows, its mentally draining trying to get them to work right out of the box.
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!
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
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 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?
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 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?
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?
This is amazing I managed to get it running but struggling to getting photorealistic results in flux. I my characters turn cartoonish. any ideas on how to improve?
@@LUCKYRABITTGet pro+ subscription from Google colab. Work in your ComfyCloud notebook. I don't think the 3070ti graphics card can run this workflow. You can try lower versions of the Flux model if you are going to work locally.
Okay total newbie here. After some time... a long time its all working EXCEPT how do I install/drop the pose sheet into the workflow. I dropped it into the workflow with the three other files given on the video but no idea how to get the pose sheet where it should be. Thanks in advance.
Great video! Although, Im in a different situation here. I have a character with mask (so no facial expressions needed) and a full body costume. I have pictures of this character from all different angles and simply want to train an AI model with this character and put him into different environments and then run image to video AI on it. I've done some tests with Runway, but it doesnt really work well as the AI keeps changing the iconic facial mask. So my problem here is consistency. Any ideas on how you guys would do this?
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?
Great video, just what I've been looking for; and I ALMOST managed to do it. I fixed a few problems (of my own making) but ended up with generation stalling at 76%. Gave up after 4 hours. Guess I'll have to wait for Runway to give me this functionality :)
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 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.
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.
I had similar problems with pulid when following another guide. I found that ua-cam.com/video/o_JOs56Q3zk/v-deo.html&ab_channel=CodeCraftersCorner had a solution. The guy goes very slowly through each step. Be aware though that his workflow uses SDXL rather than flux but that will not affect the pulid install. Good luck
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
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.
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!
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
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 🤣😂
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.)
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 ❤🔥
I'm speechless, simply amazing - thank you!
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
great! You are bridging the gap for creating meaningful stories with AI animations with this kind of tutorials. Thank you!
Dude, again, thank you! I'll be one of your patreons once I'm successful!
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
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 🙏🙏🔥🔥
Today i was trying to find a way to do this to your old workflow. You are a life saver
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!
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
The workflow reveal at 2:11 made me laugh really hard. Three Mile Island ran on a simpler system.
Thanks a lot for this amazing tutorial, I have installed and love to explore in Comfy UI. Amazing Workflow!!!
This is great workflow, Easy to work for us.
EDITED: Thanks
Absolutely wonderful following the workflow and ideas. Can't wait to try and add this in a similar workflow
This was very informative, thank you for helping us make cool things with this.
Literally was searching just for this. Thank you. Such good timing.
Excellent video and explanation and thank you for sharing the workflows. 👏👏
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.
Legend.
Signed up for Patreon.
This guy is a legend! Thanks man!
This video is totally gold! I am happy I subscribed to your channel. This is amazing!!
Great, I will continue to support
I suspect this will be one of the next features of runway that they would be working on, to be able to create consistent characters from tools like video to video
We really need this for Tensorart or Shakker!! 😀
Can you make a character sheet off an existing LoRa? Rather than creating a LoRa from a one image character sheet... Thanks!
This video made a project easy I am working on for 6 months. Danke, Herr Pumpitz! Gruß aus Wuppertal!
Thank you! Amazing workflow!
Very nice! Thanx for sharing!
This is so incredibly valuable, thank you so so much!
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!
역시 최고입니다. 바로 이걸 바랬어요. 감사합니다 :)
I was waiting for this video,, thank you so much ❤❤❤
take a bow brother 🙇♂
Gimme That Jersey. Im Keon Coleman believer since day one
You're great! Once I get comfortable with ComfyUI I'll subscribe to your patreon!
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(
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
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".
Thank you. Can't wait to try this!
Amazing work 🎉
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
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?
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.
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...
Great Video Mate
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.
First off awesome work! I appreciate your videos and really enjoy your workflows. You lay them out in a logical way and it makes things way easier to pick up on.
Is there a solid method for doing this but without training the lora on their clothing? Like if I want just a face lora with no clothing bias.
What a great video! 💯It's a blast what you can do ComfyUI. I have started this week in general with generative AI and I am really eager to learn more and to challenge myself and the tech.
Unfortunately my PC has just a RTX3070 and 8GB VRAM. Just the 2 first steps (Character Generation and Upscaling) with FLUX DEV took my PC 8 hours.
I love my new hobby but the results have to come quicker than that. Is there any way with my current setup to optimize the time?
Thank you so much Mickmumpitz to ignite my passion for that topic!
how are you running at 8gb card? i have a 4070 super with 12gb and it runs out of memory for me. any ideas?
Wonderful tutorial! 👍👍
Thank you for the great tutorial! I'm wondering where to find that workflow from 15:36 though 🤔
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
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.
Thank you very much 💖 your work is great. Could you please also share a tutorial to show how to install the comfyui and the required packages? Im begginer. Thank you ❤
Thank you so much! I have a question, is it possible to create videos with your ai characters?
By far one of the most consistent Comfy UI UA-camrs. Keep it up.
Amazing video! Excellent quality! Great job mate.
I kind of need something like this, but using a PonyXL base as Flux doesn't do the type of characters I want for my work.
Can you make an PonyXL and SD1.5 workflow that works with both new characters and already generated ones? Thank you very much!
When should we expect this to work with the latest version of ComfyUI?
Thank you very much for the tutorial, is there a way to generate a full body image?
Your canvas looks really clean with straight lines etc. Ive downloaed the files but mine look really busy, also found it asking for minecraft lora. New to this but if i can get this working youve got a premium member coming your way
i just posted to him about the "get it working" problem...he uses like a million custom nodes in all his workflows, its mentally draining trying to get them to work right out of the box.
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 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!
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.
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
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?
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.
Any chance we can save the generated work and reopen the workflow afterwards to start at the same historical stage ?
非常感谢！真是太棒了！Amazing！！
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 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?
Excellent video, what hardware do you use to make the renders so fast?
speed up the video...
@@drood78 but he's talking about seconds. How long would a full workflow like this take to render on a 4090?
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?
This is amazing I managed to get it running but struggling to getting photorealistic results in flux. I my characters turn cartoonish. any ideas on how to improve?
Did you solve the problem?
@mertakkoca7309 Not really promting
And realism lora helps a bit but for some reason very cartunish.
Man how much time it is taking . M stuck at 76 % from past one hour with 16 gb ram and 3070ti
@@LUCKYRABITTGet pro+ subscription from Google colab. Work in your ComfyCloud notebook. I don't think the 3070ti graphics card can run this workflow. You can try lower versions of the Flux model if you are going to work locally.
Okay total newbie here. After some time... a long time its all working EXCEPT how do I install/drop the pose sheet into the workflow. I dropped it into the workflow with the three other files given on the video but no idea how to get the pose sheet where it should be. Thanks in advance.
Great video! Although, Im in a different situation here. I have a character with mask (so no facial expressions needed) and a full body costume. I have pictures of this character from all different angles and simply want to train an AI model with this character and put him into different environments and then run image to video AI on it. I've done some tests with Runway, but it doesnt really work well as the AI keeps changing the iconic facial mask. So my problem here is consistency. Any ideas on how you guys would do this?
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
Great video, just what I've been looking for; and I ALMOST managed to do it. I fixed a few problems (of my own making) but ended up with generation stalling at 76%. Gave up after 4 hours. Guess I'll have to wait for Runway to give me this functionality :)
Same here stuck in 76 percent . Is this cos of low ram or something else . I have 16 gb ram and 3070ti gpu man
@LUCKYRABITT not enough vram i reckon. I did some simpler from scratch tutorials and managed to run a simpler workflow ok.
@ man how much gpu memory is needed
@ which gpu u have . And how much gpu memory is needed . I have seen comments people struggling with 24 gb gpu memory lol
@@LUCKYRABITT I've got a GTX 1660. Just a baby apparently 😀
My hero!
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)
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.
Fantastic !
always look for a CONSISTENT CHARACTERS good
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.
This is awesome. It would be great if someone made a template to run this on RunPod or something. My machine could never run this.
Hi, which workflow version of your belong to the Flux Guff version. There seems to be 3 versions workflow for Flux...
It looks nice, sadly I couldn't install pulid flux, manually or with the manager, keep "missing"
same :(
Same here
I had similar problems with pulid when following another guide. I found that ua-cam.com/video/o_JOs56Q3zk/v-deo.html&ab_channel=CodeCraftersCorner had a solution. The guy goes very slowly through each step. Be aware though that his workflow uses SDXL rather than flux but that will not affect the pulid install. Good luck
@@andeeweir24 DUDE! this WORKED!!
@@andeeweir24 Thanks man, I'll try this out :)
You must be a god
thanks.. keep it going😊
thank you so much bro
Thank you!
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?
I sent you a message on Patreon. Also on my ComfyUI, PulID always fail to load, why ? In the manager it says "Import failed"
I’m looking to hire someone to work with me building characters
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
I think this method great to game asset.
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....