Mastering ComfyUI: How to Use Embedding, LoRa and Hypernetworks! - TUTORIAL

[@hanygh2240]

Wow, this tutorial on Mastering ComfyUI was incredibly helpful! I appreciate the clear instructions on using embedding, LoRa, and Hypernetworks. It made the learning process so much easier. Thanks a ton for sharing this valuable content!

[@SenshiV]

Thanks. i have seen many Comfy videos but none using or explaining Lora use or embeddings this is the first one, super useful.

[@adr3000]

da funk. i THOUGHT i was good until i saw your flow. amazing.

[@brandonflores4]

Love the background music

[@HistoryIsAbsurd]

Thanks alot you explain things very easily to digest and not too technical for the new user

[@bobbyw.6915]

Other TH-camrs make comfyui seem so complicated. Thank you for making this easy for an idiot like me lol

[@cXrisp]

Right on time again with this video! This weekend I see if ComfyUI can lure me away from A1111. I think Comfy might win...at least for some workflows.

[@centurionstrengthandfitnes3694]

Great video. Subbed!

[@Musashi246]

AMAZING video. Thanks a lot

[@incaseidie]

exactly what i was trying to understand thank you!

[@arcangeel4828]

Great and professional video! Lucky to have found u dude ;)

[@ShinsekaiAcademy]

That was very helpful, much thanks

[@nodewizard]

Thank you for the embedding tip. It's not intuitive about how you go about adding it. I've completely switched over to ComfyUI (since Stability AI supports it over A1111). Noticeably faster compared to A1111 for SDXL.

[@killbadmashia9225]

Where can we go and learn which components are used in a certain workflow to accomplish a task ? or what the workflow of Nodes would be to accomplish a certain task ?

[@rsunghun]

I wondered how to use embedding and hypernetwork. Thanks. There's not much hypernetwork on civitai. I guess it's difficult to make.

[@screamingstarprime3503]

I can’t find any examples of using Lora as a negative. Any recommendations for how to do this? I’ve tried a variety of methods, but not sure what everyone else is doing.

[@user-vx7kz9wy9i]

hi, you are very cool, thank you for your work, could you recommend a video on face replacement, I would like to do neurophoto sessions.

[@DreamingAIChannel]

Hi, thanks! Yes, you can watch this one th-cam.com/video/gcLBPILYgrc/w-d-xo.html

[@AdvancExplorer]

Hello my friend, can you tell me how are you set "perpendicular" cables between nodes in comfy ui, thanks a lot

[@DreamingAIChannel]

Hi! if you mean the straight line , i've explained it here: th-cam.com/video/AjwfswzLmxU/w-d-xo.html

[@AdvancExplorer]

@@DreamingAIChannel I just find the vidéo when you talk about this when i see your comment 😄 thanks

[@m.a6416]

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

[@shuanshuanzai]

You show a complex workflow,which looks so adv, but it's not a good demo. Where is your embedding string connected to ?

[@lastlight05]

Do you have tutorials on setting up a workflow like this? I want to know how to build an in-depth workflow but don't know where to start or how all of the different nodes work together.

[@DreamingAIChannel]

Hi! If you mean the very basics of ComfyUI, yes I have it! Look at this one: th-cam.com/video/ikYtP0ThN5A/w-d-xo.html Otherwise you can try to search in my past videos if you find something useful to you! ❤️

[@haroldrandolf2981]

Hey there! Im getting this error while loading the workflow -
When loading the graph, the following node types were not found:
String Variable
Nodes that have failed to load will show as red on the graph.

[@DreamingAIChannel]

Hi! You can just replace the string node with a primitive node if you want, otherwise the String Variable is part of my custom nodes suite that you can download from here: github.com/Nuked88/ComfyUI-N-Nodes

[@haroldrandolf2981]

@@DreamingAIChannelthank you very much. I just have one more question.
I have been trying to generate some ummm spicy images but I cant seem to do so with sdxl 1.0 base model. I'm using ComfyUI coz I cant seem to run Automatic1111 or Vladmandic.
Is it ComfyUI's problem?
Also I used absolute reality model from civitai and its generating what I want but it is again censoring my images if I try to send it to sdxl 1.0 refiner model.
Can you please help me?

[@DreamingAIChannel]

@@haroldrandolf2981 well no, it's not a ComfyUI problem, I think is just the sdxl base and her refiner that are censored. Just search if there are any uncensored versions of those models or just don't use the refiner with Absolute Reality!

[@haroldrandolf2981]

@@DreamingAIChannelOh thank you very much. You have earned one sub :)
Just one last thing and I promise its the last . When im trying to install ur custom nodes and running install_dependency it says this error:
ERROR: Exception:
Traceback (most recent call last):
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\cli\base_command.py", line 180, in exc_logging_wrapper
status = run_func(*args)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\cli
eq_command.py", line 248, in wrapper
return func(self, options, args)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\commands\install.py", line 377, in run
requirement_set = resolver.resolve(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib
esolver.py", line 92, in resolve
result = self._result = resolver.resolve(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 546, in resolve
state = resolution.resolve(requirements, max_rounds=max_rounds)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 397, in resolve
self._add_to_criteria(self.state.criteria, r, parent=None)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 173, in _add_to_criteria
if not criterion.candidates:
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor
esolvelib\structs.py", line 156, in __bool__
return bool(self._sequence)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 155, in __bool__
return any(self)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 143, in
return (c for c in iterator if id(c) not in self._incompatible_ids)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 47, in _iter_built
candidate = func()
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\factory.py", line 206, in _make_candidate_from_link
self._link_candidate_cache[link] = LinkCandidate(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 293, in __init__
super().__init__(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 156, in __init__
self.dist = self._prepare()
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 225, in _prepare
dist = self._prepare_distribution()
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 304, in _prepare_distribution
return preparer.prepare_linked_requirement(self._ireq, parallel_builds=True)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\operations\prepare.py", line 538, in prepare_linked_requirement
return self._prepare_linked_requirement(req, parallel_builds)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\operations\prepare.py", line 653, in _prepare_linked_requirement
dist = _get_prepared_distribution(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\operations\prepare.py", line 69, in _get_prepared_distribution
abstract_dist.prepare_distribution_metadata(
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\distributions\sdist.py", line 48, in prepare_distribution_metadata
self._install_build_reqs(finder)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\distributions\sdist.py", line 118, in _install_build_reqs
build_reqs = self._get_build_requires_wheel()
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\distributions\sdist.py", line 95, in _get_build_requires_wheel
return backend.get_requires_for_build_wheel()
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_internal\utils\misc.py", line 697, in get_requires_for_build_wheel
return super().get_requires_for_build_wheel(config_settings=cs)
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor\pyproject_hooks\_impl.py", line 166, in get_requires_for_build_wheel
return self._call_hook('get_requires_for_build_wheel', {
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor\pyproject_hooks\_impl.py", line 321, in _call_hook
raise BackendUnavailable(data.get('traceback', ''))
pip._vendor.pyproject_hooks._impl.BackendUnavailable: Traceback (most recent call last):
File "C:\Users\ayaan\Desktop\ComfyUI_windows_portable_nvidia_cu118_or_cpu\python_embeded\lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 77, in _build_backend
obj = import_module(mod_path)
File "importlib\__init__.py", line 126, in import_module
File "", line 1050, in _gcd_import
File "", line 1027, in _find_and_load
File "", line 992, in _find_and_load_unlocked
File "", line 241, in _call_with_frames_removed
File "", line 1050, in _gcd_import
File "", line 1027, in _find_and_load
File "", line 1004, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'scikit_build_core

[@DreamingAIChannel]

re-download the custom node now, (or update it with git pull), i made some changes so it's possible to use it even if you don't want to use the GPT node

[@fillill-111]

But - where do you connect this dots, how do you connect lora? How and where should it be connected?(:

[@Vestu]

I think you can just list the different embeddings in single (embedding: )
Like (embedding:bad_artist,badhands,badwhatever) etc.

[@DreamingAIChannel]

ohh i didn't knew that! Thanks! Is it possible to change the strength with this syntax?

[@kryless7775]

ty

[@timtarbet4594]

How do you download your workflow? I click on the link and just get a mess of text that I don't know what to do with.

[@mehradbayat9665]

What's the difference between 'strength_clip', and 'strength_model' in the lora loader?

[@jongk9360]

strength model determines the strength you wanna apply on, clip sets the cap for it. if you put strength model at 0.4, clip at 0.2, it will only use the 20% potential from the strength you set which is 40%

[@nishwithdilani]

Hi,
how did you achieve the 'square noodles' ? - TIA

[@TheRMartz12]

they are a custom node, I cant remember the name right now but you should be able to google it and find it easily

[@DreamingAIChannel]

Hi! here i've explained how to put the straight lines: th-cam.com/video/AjwfswzLmxU/w-d-xo.html

[@edwardwilliams2564]

How do you go about getting your connections to look like that, instead of the spagheti look they come with?

[@DreamingAIChannel]

Hi! Here i've explained how to put the straight lines: th-cam.com/video/AjwfswzLmxU/w-d-xo.html

[@edwardwilliams2564]

Thanks.@@DreamingAIChannel

[@michaelchu6516]

how do you make the lines flow straight like that? My workflows look like a bowl of spagetti or a box of tangled cords

[@DreamingAIChannel]

Hi! i've explained it in this video: th-cam.com/video/AjwfswzLmxU/w-d-xo.html

[@CrisisBomberman]

not really practicale cause u need to type all with hand instead of clicking somewhere to write whole trigger

[@bohguss]

This AI voice is worse than real Joe Biden hahaha

[@CanadaBlue85]

adding "uhms" to an AI voiceover script sounds.....weird and off putting

[@DreamingAIChannel]

I'm not "adding" anything man, but I like the uhms😊