Відео

This was trash, there goes 13 minutes.

Disgusting AI voice for the love of god just use a mic you sicko

HI WHICH wd-v1-4-tagger- OF U DOWNLOAD

I love that you don't show your face and voice, but I'd like you to make more advanced, in depth tutors

Hey mate, what an amazing workflow you created, I have a simple question will this work to create full-body poses from face only images? Trying to make best Lora for my character which I sadly created from half body image and now struggling little bit to perfect rest of the body to fit neck, head and shoulders. Thanks in advance. ☺️

this doesn't when i use runpod's url

For anyone getting an error that says something like: !!! Exception during processing !!! mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320) or !!! Exception during processing !!! Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 16, 64, 64] to have 4 channels, but got 16 channels instead This may be caused by the use of a wrong checkpoint model. it seems that the ipadapter needs SD1.5 to work properly and in my case i tried using SDXL and SD3. I hope this helps most people in this situation

wasnt able to build the workflow, i download everything and have all the nodes but it wont allow me to connect them the way you did in this video. granted this was posted a little over a year ago so maybe its been updated. im a noob so i just dont know

Nice tutorial, Thanks!!

2:50 *Topaz Video AI latest versions are able to make smooth videos even from videos with a frequency of 5 frames per second, as if they were shot with a high-speed camera, miracles!*

안녕하세요 영상 잘 보고 있습니다! 설치를 하면 ERROR: To modify pip, please run the following command: C:\Users\PC\AppData\Local\Programs\Python\Python310\python.exe -m pip install -r requirements.txt 이런 문구가 뜨는데 어떻게 해야 할까요?ㅜㅜ

The the UI can't find the LoadVideo node though says the plugin is installed. Any ideas?

I wonder if there is some service or tool where it is possible to play a role-playing game with chat but at the same time assign your own images to the characters? Those. for each character? Or make a transition to locations where an image of, say, a “tavern” appears when you mention going to that location? Damn, this could be done by a wildly popular service with such ideas...

I have no Idea how you got the "lora caption load" space there. I try to search but can't find it. My search space looks different than yours also.

Hey, can you help me? i'm having this problem with ipa unified loader "IPAdapterUnifiedLoader IPAdapter model not found." and i use comfyui manager, and instaled the clips from there, but still with this error.

can you update with FLUX?

hey i was trying comfy ui for video to video for the first time, so i was following your workflow, but when i went to the 2nd step "save video" it didnt appear on the box. Can you help me?

why I can't find python_embeded folder

I. Am. Gobsmacked. It actually worked. This is like the backdoor to the matrix. Thank you.

Awesome work again, big thanks!

after getting comfy-ui custom scripts so that I may adjust the denoise value in the ksampler, described at around 11:44, I cannot move anything around, zoom in or out, I can only double click on the screen to search for custom nodes. I'm Using GPT to try to figure it out, can't find a solution online. I deleted the custom node but something is not resetting. EDIT: I was trying to rename my original folder to try something with a fresh install, and for some reason it kept saying comfyUI was opened even though I had closed it completely. Perhaps this had something to do with locking up my controls. I shut down my computer and restarted it, works now. EDIT2: Everything seems to work properly however I'm getting a "stack expects a non-empty tensor list" so then whatever it is that converts the frames into tensors is not providing a list. At 10:59 as you back tracked over the entire setup, I noticed that "Load Frames from folder" node spoken about at 6:01 is not there at all... perhaps this has something to do with it? If so, I'm not sure where to hook it up, I'm not yet too familiar with the placement of nodes yet - day 2 using comfy rn.

This AI voice is worse than real Joe Biden hahaha

Easy to follow and greatly explained. However my question is: in this case you got a picture and a sketch combined, so the IPadapter only resulted in a merge of both. What if I don't load any picture as reference and I only want the model to interpret the prompts and the sketch? Would that work, or do I need a secondary image as a reference? In addition, can I load loras from the prompts directly into the generation?

Where do we get the LoadVideo node?!

i tried again with python 3.10.11 installed instead of 3.12. and i got to the 1:41 part of your video and when I entered that command to install that whl file I was told by terminal: "ERROR: insightface-0.7.3-cp310-cp310-win_amd64.whl is not a supported wheel on this platform."

I cant get through 1:47, the error that comes up is: ERROR: insightface-0.7.3-cp312-cp312-win_amd64.whl is not a supported wheel on this platform im trying to use a windows machine with very limited knowledge of windows since I use mac all the time

Hi,Thank you, it is a nice tutorial, I would like to use inpainting to show a model/character showcasing product in hand or any other way, I will look forward to try this , also doing this in a video would be excellent

Could you possibly download a new comfyui portable and show us how to setup the current version of reactor for the first time? I had it setup before, got a new computer, lost everything, and cant get the current version running. Ive tried multiple times, watched many videos and articles, just cant get it. Love your channel ❤

Error occurred when executing GPT Sampler [n-suite]: The expanded size of the tensor (749) must match the existing size (750) at non-singleton dimension 1. Target sizes: [1, 749]. Tensor sizes: [1, 750] Any solutions?

Thank you so much for combining Rob Adam's workflow into a node. I was struggling to recreate it in the same way he did. Appreciate it!!!

I am getting a bunch of errors when installing ReActor custom node. It fails to get requirements to build wheel. It says "ModuleNotFoundError: No module named 'Cython'" Subprocess exited with errors.

"ERROR: Could not install packages due to an OSError: [WinError 206] The filename or extension is too long:" Any idea on how to solve this?

How do you add a lora loader. Just saw a search bar out of nowhere

I love this guy. Thank you for starting from blank.

Do you offer workflows with your membership? I would love a workflow with this setup but with a flux model

im experimenting with t2v within comfyui using sdxl checkpoints but im failing miserably, just getting static images. is animatediff not working with this? my checkpoint im trying to use is ponyv6

ModuleNotFoundError: No module named 'onnx' I receive this message despite having insightface installed properly

Great content thank you.

How to proper prepare dataset to train on specific word or logo? My lora's saves style but not precise shapes

Hello! Amazing video but I keep getting this on the terminal, after a few seconds... any straigt forward solution? is this related to my python or ccomfyui version?? Thank you!! c parameters or run `accelerate config`. C:\Users afax\AppData\Local\Programs\Python\Python310\python.exe: can't open file 'C:\\Users\ afax\\Documents\\ComfyUI_windows_portable\\custom_nodes\\Lora-Training-in-Comfy\\sd-scripts\\train_network.py': [Errno 2] No such file or directory Traceback (most recent call last): File "C:\Users xxxxxx\xxxxxx\Local\Programs\Python\Python310\lib unpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users xxxxax\xxxxxx\Local\Programs\Python\Python310\lib unpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\xxxxxx\xxxxx\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 996, in <module> main() File "C:\Users\xxxxx\xxxxx\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 992, in main launch_command(args) File "C:\Users afax\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command simple_launcher(args) File "C:\Users\xxxxxx\xxxx\Local\Programs\Python\Python310\lib\site-packages\accelerate\commands\launch.py", line 628, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['C:\\Users\\xxxxx\\AppData\\Local\\Programs\\Python\\Python310\\python.exe', 'custom_nodes/Lora-Training-in-Comfy/sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=C:\\Users\\xxxxx\\Documents\\ComfyUI_windows_portable\\ComfyUI\\models\\checkpoints\\epicrealism_naturalSinRC1VAE.safetensors', '--train_data_dir=C:/database', '--output_dir=C:\\Users\\xxxxx\\Documents\\ComfyUI_windows_portable\\ComfyUI\\models\\loras', '--logging_dir=./logs', '--log_prefix=myscreen', '--resolution=512,512', '--network_module=networks.lora', '--max_train_epochs=400', '--learning_rate=1e-4', '--unet_lr=1.e-4', '--text_encoder_lr=1.e-4', '--lr_scheduler=cosine_with_restarts', '--lr_warmup_steps=0', '--lr_scheduler_num_cycles=1', '--network_dim=32', '--network_alpha=32', '--output_name=myscreen', '--train_batch_size=2', '--save_every_n_epochs=100', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=20', '--cache_latents', '--prior_loss_weight=1', '--max_token_length=225', '--caption_extension=.txt', '--save_model_as=safetensors', '--min_bucket_reso=256', '--max_bucket_reso=1584', '--keep_tokens=0', '--xformers', '--shuffle_caption', '--clip_skip=2', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard']' returned non-zero exit status 2. Train finished Prompt executed in 3.09 seconds

I have a LEGION 5 laptop, Ryzen AMD, NVIDIA GEFORCE GTX 1660 6GB graphics card, do you think it can work? I ask because I have tried several tutorials and they all vote error in KSAMPLER or UNSAMPLER, or do you have any help for my case?

How to install that searching menu? i can't find a node well.

Great video. Subbed!

That was very helpful, much thanks <3

I wanted to use more than 3 checkpoints with more than 3 loras, is it possible on comfyui?

When I Queue my prompt to Train, It 'runs' for a moment but no cmd window pops up and no file is created... Not sure what I am doing wrong?

Thank you very much the first real video that explains what LoRA's are so that we understand what to do.

im having trouble, my loadvideo wont show in my savevideo when i connect them, is there something i need to do extra in order for it to load?

10 months later, what is the best solution for inpaint for ComfyUI? Thanks!

kill the bg music