6 ай бұрын
7 ай бұрын
8 ай бұрын
9 ай бұрын
10 ай бұрын
Пікірлер
@Epulsenow 6 сағат бұрын
Hi, I tried steps of generating an image with a reference image. The first way you shown. But it did not work. Any suggestions?
@ImagindeDash 21 сағат бұрын
Thank you for the tutorial but I´m getting this error: Error occurred when executing LayerUtility: ImageBlendAdvance V2: 'NoneType' object is not iterable
@controlaltai 21 сағат бұрын
Not sure what is this error, could be some connections are wrong. Ensure background and layer are correct.
@SaoirseChen-v8b Күн бұрын
Thank you for the incredible workflow, I got an issue when generating the ksampler before the details and color adjust parts, the ksampler image became total black at 60%, and the colormatch got error(stack expects a non-empty TensorList), do you have any clues?
@controlaltai Күн бұрын
Hi, Not untill I see what you have done with the workflow. It's quite complex to identify the issue. You mail me, I can have a look and see if I can troubleshoot it. mail @ controlaltai . con ( without spaces)
@user-yg4qo9zg3u 2 күн бұрын
I tried the workflow (15:15 Face Details) . and I got the following error: Error occurred when executing BLIP Analyze Image: 'BLIP_Decoder' object has no attribute 'generate_caption'. As far as I understand, I am using the wrong BLIP model/Analyzer?
@controlaltai 2 күн бұрын
Download the latest version of was node and use the defaults. It's a bit different than what's shown in the video as it's updated recently. You can try other nodes as well like gemini, ollama, florence2. All you need is some llm to describe the image.
@user-yg4qo9zg3u 7 сағат бұрын
@@controlaltai Wow, thanks a lot! So much info and great video!
@LolyphotoWedding 2 күн бұрын
Updated: ComfyUI: 2445[369f45](2024-08-01) The MultiArea Air Conditioning button cannot be used. Do you have any way to fix this problem?
@controlaltai 2 күн бұрын
I had no issues with it. Will recheck with the last update. What error are you getting?
@controlaltai 2 күн бұрын
Hi, Just tried it with everything updated. No issues here. You have to tell me what exactly the issue is.
@LolyphotoWedding 2 күн бұрын
@@controlaltai After updating to the new version. The button has a red flag but I can't fix the error. I can't find the Multi-Zone Air Conditioning button even though I've deleted and reinstalled it. I hope you can suggest troubleshooting instructions. Thank you!
@controlaltai 2 күн бұрын
You have to tell me the cmd error. When you delete and reinstall you have to close cmd and restart comfy fully. If you are still facing issues email me with the error to mail @ controlaltai . com (without spaces).
@ismgroov4094 2 күн бұрын
i have error,sir. "Given groups=1, weight of size [320, 4, 3, 3], expected input[1, 8, 104, 152] to have 4 channels, but got 8 channels instead"
@controlaltai 2 күн бұрын
Is layered diffusion custom node installed?
@ismgroov4094 2 күн бұрын
@@controlaltai i did sir
@ismgroov4094 2 күн бұрын
@@controlaltai there is something wrong with "Ic light apply" node.. plz help me.
@controlaltai 2 күн бұрын
Choose the fc model and not fbc. Download the correct models from the link. This is the ldm version of models and not what's given on kijai GitHub.
@ismgroov4094 2 күн бұрын
@@controlaltai thx sir, isolved sir! ❤️🙏🏻🥹
@Hycil2023 4 күн бұрын
context is the multiplier for 75 token size, setting the max to 128 will slow down tensorRT a lot and increase vram, for average use case it should be set to around 2-4 (about several dozen tags worth)
@agusdor1044 4 күн бұрын
Thank you for your great work! I tested the workflow on a cloud GPU service because my PC isn't that powerful, and I'm getting this error: Error occurred when executing LayerMask: BiRefNetUltra: [Errno 2] No such file or directory: '/ComfyUI/models/BiRefNet/swin_large_patch4_window12_384_22kto1k.pth Do you have any idea how I can fix this? I forgot to mention that I used the Manager, and all installations are correct. The BiRefNet models are actually accessible, but I'm not sure if it might be related to something else on the platform I'm using.
@user-rk3wy7bz8h 4 күн бұрын
Hi. I need a trick to use higher gpu Vram. For example i have 2 PC and want to render with both. Do you know a solution for that? There is a node called NetDist, but its very bad documented i am lost. Maybe you are smarter than me and could help somehow ?
@josephmorgans6812 4 күн бұрын
great work, thank you ! Is it possible to edit / change the background & product (STRING) promts ?
@controlaltai 4 күн бұрын
Yeah, you can use custom conditioning. A switch is given in the workflow. Copy and paste from the Ollama generation to custom text condition, then make the switch to 2.
@josephmorgans6812 4 күн бұрын
@@controlaltai Thank you for your quick reply. Sadly it does seem to work for me, the final image doesn't change.
@controlaltai 4 күн бұрын
Send me your current workflow with the prompt the reference bg and the product image to mail @ controlaltai . com (without spaces). The workflow is complicated, obviously something is missed. Will have a look and revert to you via email.
@brividoboy 5 күн бұрын
Thank you. Your tutorials are the best here. Detailed and simple.
@KeenHendrikse 5 күн бұрын
Hey, can anyone advise where I can find the image blend advanced v2 node?
@controlaltai 5 күн бұрын
LayerStyle Custom Node. Check video custom node requirements.
@Jason-c-i4g 7 күн бұрын
I'm getting an error: "Error occurred when executing IPAdapterAdvanced: The size of tensor a (257) must match the size of tensor b (577) at non-singleton dimension 1"...any ideas/suggestions on how to get this running properly? I've followed all the advice on updating IPAdadpter to IPAdapterPlus and have everything configured (as far as I know) correctly...
@controlaltai 7 күн бұрын
You have to tell me on which node you are getting the error? The node would be highlighted red or purple in comfy.
@Jason-c-i4g 7 күн бұрын
@@controlaltai It shows IPAdapter Advanced (in the IPAdapter group, the one that has replaced the deprecated Apply IPAdapter node)
@controlaltai 7 күн бұрын
It's the ip adapter model and clip vision model in compatibility. Also the checkpoint should be sdxl. Select the plus vit h sdxl ip adapter model with vit h clipvision and base sdxl checkpoint. Ensure all ControlNet are sdxl controlnets.
@KashifRashid 7 күн бұрын
I have installed everything but I cant find the switch (any) node on my search . What am I doing wrong?
@KashifRashid 7 күн бұрын
Ok.. figured that one out.. lol. Had to update comfyui from outside. not the manager
@asmedeus448 8 күн бұрын
I try to use multiareaconditioning with LORA on each prompt. the output image generate independent crop which is it not really great.
@controlaltai 7 күн бұрын
Can you share your workflow and lora via email. I can have a look, email me at mail @ controlaltai. com without spaces
@asmedeus448 7 күн бұрын
@@controlaltai hi, thanks for the fast reply. I'll send you tomorrow with the workflow of the prompt
@CORExSAM 8 күн бұрын
you sound like some character from game of thrones fr
@controlaltai 8 күн бұрын
Its an AI voice. And no, its no one from that show, just randomly picked and stayed with it. Works better for presentations style video tutorials.
@CORExSAM 8 күн бұрын
@@controlaltai oh sorry nevermind, i commented on wrong video LOL
@design38 8 күн бұрын
Hi, great tutorial, by the way! I have a slight problem. The resulting image of a black product is different from the original. For example, if the product is black running shoes and the background is a green scenery, the result will make the shoes appear green. I also tried a black bag, and it turned white. the details is still there, but this result is after ksampler. probably has something to do with the IPAdapter or IClight ??
@controlaltai 8 күн бұрын
Hi, Send me the workflow and the images to mail @ controlaltai . com (without spaces), without looking and testing myself, can’t trouble shoot.
@CharlesPrithviRaj 8 күн бұрын
couldnt find the birefnetultra node, which custom node is it from ?
@controlaltai 8 күн бұрын
That's from LayerStyle custom node.
@michaelbrandonfalk5316 8 күн бұрын
Well this is where I stop tonight " Error occurred when executing UNETLoader: ERROR: Could not detect model type of: C:\ComfyUI_windows_portable\ComfyUI\models\unet\IC-Light\iclight_sd15_fc.safetensors " got to retrace the steps again I guess
@controlaltai 8 күн бұрын
Okay so you have downloaded the wrong models. Check models in requirements or check description. You have to download the layered diffusion version of the model. Here is the link huggingface.co/huchenlei/IC-Light-ldm/tree/main
@michaelbrandonfalk5316 8 күн бұрын
@@controlaltai ahhh, I was thinking that could be it. Thank you so much for your patience. Now I can sleep :)
@princeyadav0350 8 күн бұрын
How much vram needed i have 16GB, is it enough?
@controlaltai 8 күн бұрын
More than enough.....for the basic workflow.
@michaelbrandonfalk5316 8 күн бұрын
at 30:00 you mention copying the negative prompt from CivitAI, could you expound on this? Thanks!
@controlaltai 8 күн бұрын
Well all i did was opened sample images from juggernaut aftermath and checked the negatives used. Copy and pasted that. That's what I meant.
@michaelbrandonfalk5316 8 күн бұрын
@@controlaltai ooooh that makes sense. Thanks
@LucasMiranda2711 9 күн бұрын
Doesn't seem to work on new versions of comfyui unfortunately
@controlaltai 9 күн бұрын
I have just tested this after your comment, like 2 minutes back on the latest version of comfy, in the matter of fact my comfy uses the nightly PyTorch version, everything works as intended. I just ran all the workflows to double check.
@LucasMiranda2711 6 күн бұрын
@@controlaltai the project from davemane is archived on his github and the node doesn't even appear on filter from comfyui, trying to install it from github, when creating the node the screen freezes from exceptions
@controlaltai 6 күн бұрын
The one that freeze is muLti latent composition, not area conditioning. Check which node you are putting, he has two node, one always had problems, the workflow doesn’t use latent composition.
@SanchezGodsent 9 күн бұрын
i have this problem: Error occurred when executing LayerUtility: HLFrequencyDetailRestore: images do not match
@controlaltai 9 күн бұрын
Yeah if you don't put a manual mask you get that error. It passes on an empty image which is a mis match. Have mentioned this in the video. So connect your image to the preview bridge. Get the error, then manually mask and save the preview bridge and run queue prompt again. It should go through.
@bizonlarheryerde 9 күн бұрын
Is your channel’s membership option turned on? I can’t see it anywhere.
@controlaltai 9 күн бұрын
Yes, here is the link: kzfaq.info/love/gDNws07qS4twPydBatuugwjoin
@jjagdishwar 9 күн бұрын
Love this. Thank you so much
@DanielPartzsch 9 күн бұрын
Very nice. What exactly is the difference between the old IC light models and the once you've used here? Do they yield better results? Thanks
@controlaltai 9 күн бұрын
Actually this one is older, it came out first I think. I started with kijai, all respects to him for his work. However I was not getting the results that I wanted. I switch to an entire different way as the way this one works is different, was impressed with the results, just went on building the workflow from there. Don't have a side to side comparison as the nodes and method applied are both different. So I cannot be sure if any is better, as I really did not go back to the kijai one and tried to get that working the way i wanted.
@michaelbrandonfalk5316 9 күн бұрын
Thank you. How does one install the VIT MATTE detail model, Pymatting is working for me in Ultra, but I seem to be missing VIT MATTE
@controlaltai 9 күн бұрын
I have explained in the video. Check from 6:28
@michaelbrandonfalk5316 9 күн бұрын
@@controlaltai Thank you! That's what I was looking for!
@michaelbrandonfalk5316 9 күн бұрын
@@controlaltai BTW are you on LinkedIn ? I did a post about this tutorial and would love to tag you. Thanks again for the great tutorial!
@controlaltai 9 күн бұрын
Hi, no went off LinkedIn years back. That's fine feel free to share.
@michaelbrandonfalk5316 8 күн бұрын
@@controlaltai not gonna lie I originally skipped that section, and really wish I had not. Going back through it now :)
@ameerziadi4253 10 күн бұрын
can you share workflow
@controlaltai 10 күн бұрын
Ready made json files are for channel paid members only. You can just build the workflow following the tutorial. Nothing is hidden.
@SanchezGodsent 9 күн бұрын
@@controlaltai where i this private channel?
@controlaltai 9 күн бұрын
KZfaq Join Membership
@kobe5113 10 күн бұрын
honestly this is too good, thank you so much
@kobe5113 10 күн бұрын
really really well done
@esuvari 10 күн бұрын
Oh MY GOD! This is incredible! The first two random images I tried off the top turned out amazing, first try. You're the most underrated SD channel on youtube, thank you for this amazing work. Can't wait to get my hands dirty with this. Wish you the best.
@yuvish00 9 күн бұрын
Hi, did you get the error: Given groups=1, weight of size [320, 4, 3, 3], expected input[1, 8, 104, 152] to have 4 channels, but got 8 channels instead ?
@esuvari 9 күн бұрын
Nope, it worked on mine
@GoodArt 10 күн бұрын
that was just the coolest video I've ever seen. comfy rules.
@jd38 10 күн бұрын
Yes, finally! thank you for this tutorial
@PrithivThanga 10 күн бұрын
Must be a worthy one. will test and post here..
@controlaltai 10 күн бұрын
IC-Light is based on SD1.5, but all generates are SDXL Resolution, then 4x Upscale. I hope you find the tutorial helpful. Please note: at 5:17 layered diffusion custom node is needed, even though no nodes are used otherwise you will get an error as follows: RuntimeError: Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 8, 64, 64] to have 4 channels, but got 8 channels instead
@williamsaton8812 6 күн бұрын
thx sooooo much
@ivanivan9301 3 күн бұрын
Thank you so much, I followed the video for 2 days and finally managed to make it, awesome tutorial! 👍
@ismgroov4094 2 күн бұрын
sir help me!!!!! i bought your workflow :( ... plz
@controlaltai 2 күн бұрын
Already replied to you.
@juxxcreative 10 күн бұрын
Any chance to get downloadable workflow ?
@controlaltai 10 күн бұрын
Everything is shown in the tutorial and can be replicated, in the sense that the technique and know how is not hidden behind a paywall. However, paid channels members have access to the json workflow along with the assets used.
@juxxcreative 10 күн бұрын
@@controlaltai ok thnx
@user-pp9xw9mc5k 11 күн бұрын
bro you are fucking god to me
@THEJATOXD 11 күн бұрын
Is there any update on this? i'm still having the For error: "cannot import name 'packaging' from 'pkg_resources'" error
@controlaltai 11 күн бұрын
Yeah, I posted in the pinned post. Reposting for you again.... For error: "cannot import name 'packaging' from 'pkg_resources'" The solution: Ensure that Python 3.12 or lower is installed with a comfy UI portable. Then go inside ComfyUI_windows_portable\python_embeded folder and run this command. python.exe -m pip install setuptools==65.5.1 A comfy update installs setuptools-70.0.0, you need to downgrade for it to work.
@THEJATOXD 10 күн бұрын
@@controlaltai hey i tried doing that and I was not successful, still had the error, any suggestions?
@controlaltai 10 күн бұрын
Something else is wrong. That has to do with some dependency version. If you are on portable that the dependency command should be in the comfy python folder. Double check the version. Also check your portable python version. It should be lower than 3.12 I have double checked it and it works. Unless python is at 3.12
@CerisCinderwolf1 12 күн бұрын
When installing via the URL, I run into: stderr: ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'D:\\stable-diffusion-webui\\venv\\Lib\\site-packages\\cv2\\cv2.pyd' Check the permissions. ControlNet init warning: Unable to install insightface automatically. However the message in Automatic1111 gui says "Installed into D:\stable-diffusion-webui\extensions\sd-webui-controlnet. Use Installed tab to restart." I've done what digging I could on this and a few people have reported but but there's never a consensus on what to do to fix this. Any thoughts/ideas? There's only one user account on this pc (mine and it has full admin priviledges). I don't run SD (Automatic1111) in admin mode as that can cause issues down the road. I've installed other extensions just fine from within Automatic1111 using the URL functionality.
@controlaltai 11 күн бұрын
It's a permission error. Checkout the GitHub page for solutions. Running in admin mode solves it.
@CerisCinderwolf1 12 күн бұрын
Loving the guide so far but running into a problem and have a question- you used a ControlNet for the clothing but during the installation, didn't talk about enabling/installing ControlNet with ADetailer. Currently that dropdown doesn't open/is grey as if I have no controlnets. Where might I go hunting for this if something's missing? This is a fresh install as of watching your video :)
@controlaltai 12 күн бұрын
Thanks. The interface might be slightly different since the video is old. However here is everything you need to know about control net with a1111. The basics atleast. kzfaq.info/get/bejne/gMpzrKp8u82se30.html
@CerisCinderwolf1 12 күн бұрын
@@controlaltai I appreciate your reply and the link! I'm already running into the one most common issue with ControlNet installation (the dreaded "WinError 5: Access is denied"). I'll post over there though since it's a video specific to ControlNet! :)
@ultimategolfarchives4746 12 күн бұрын
Hello sir. Were you able to make it work with cosxl models?
@controlaltai 12 күн бұрын
Hi. Doesn't work. Not compatible for the moment. Tried and tested.
@ultimategolfarchives4746 12 күн бұрын
@@controlaltai Sounds good. Thank you for your answer. Been following you for a little while now, and your videos are gold sir. Thanks
@op12studio 12 күн бұрын
Holy crap this was good... I love being able to just boop people out of pictures now lol
@emizemani6958 13 күн бұрын
Amazing work! Just one question, in the combined workflow, how do you add a mask manually? Because the moment I queue prompt the mask disappears from the preview bridge. Am I doing something wrong?
@controlaltai 13 күн бұрын
Thank you. That is normal. The preview bridge is a live stop over node. If the source before that regenerates the preview bridge will refresh. If you have masked once and want to re use that same mask replace the preview bridge or make a side connection with a node called load image as mask. And load the mask there.
@emizemani6958 12 күн бұрын
@@controlaltai thank you for your reply! I tried what you suggested and it worked. Just another question, is there any way to have all of those workflows in one comfy tab?
@controlaltai 12 күн бұрын
@@emizemani6958 Welcome and Yes. Update Comfy to the latest version. Go to settings, there should be a beta option at the top. Enable by setting the bar position at the top or bottom. You will also get the workflow management in this Beta. You can load multiple workflows in one tab.