ComfyUI Full Workshop — first workshop from ComfyAnonymous himself!

Channel: aiDotEngineer

Published at: 2025-07-19

YouTube video id: _FKeSzM9fPc

Source: https://www.youtube.com/watch?v=_FKeSzM9fPc

[Music]
Uh, good morning everyone. I am Yedri
Kosinski and this is
Yeah. Hello. I am known online as a
comfy anonymous, the original creator of
Comfy UI.
and we are part of the Comfy or the
organization that uh is in charge of
Comfy UI.
So uh I guess now I have a mic. I'll ask
again who here has heard of Comfy UI?
All right. All right. This half of the
room very knowledgeable, very nice, very
nice. Um, for those unaware, we are an
open- source note-based design canvas
intended for generative AI purposes for
uh multimodal um creative applications.
We support image, video, audio, 3D,
text, and more uh generative AI models.
Um, Comfy UI supports the absolute
bleeding edge of generally itch on day
one. We have Comfy Anonymous here
implementing it from not quite scratch
but it is redesigned from the original
implementations. Uh, we offer open-
source locally hosted models that
support Nvidia, AMD and Intel hardware.
And we also support closed source API
accessible models that we as the name
suggests just use an API to deliver to
the user.
All this functionality is also
extendable with community supported
custom notepads. So anything we do not
have the time to get to ourselves, the
community does for us.
A big part of what makes Comfy UI
special is the sharability of the
workflows. Any image or video that was
generated by Comfy UI has embedded
metadata that lets you drag it back into
the canvas and brings you the original
workflow with all of the parameters that
was used to generate it.
Uh this sort of sharability and virality
has really helped Comfy UI's traction.
If you do a simple Google search on uh
Comfy UI workflows, you will find pages
and pages and pages of results from the
past year and a half, most of which are
still compatible with modern Comfy UI
versions.
Um,
in terms of pure numbers, uh, this sort
of share billion virality has over the
past two years taken us to the position
of top 150 most popular GitHub repos of
all time with 78,000 stars.
Any comments? Comfy?
Uh, no.
All right. All right.
uh with more of the traction numbers. We
have 3 to four million active users. We
have 20K daily downloads. We have 22,000
custom nodes made by 3,000 public
developers that we enable in our
ecosystem. And we've been adopted by
Amazon, Apple, Tensson, Netflix, and
more. And pretty much any startup these
days built around visual generative AI
probably has come UI working somewhere
on their back end.
Um, why is Comfy UI popular? Um, it
gives maximal control. You can go beyond
prompts and interact with models that
give you access to depth maps, line art,
uh, masks, anything like that that is
out in the space. If it's if it's open
source, we probably either support it
directly or the community has uh, made
it possible. We are an all-in-one
platform for both exploration for
creatives and automation for developers.
Sometimes those roles can also be
switched where developers want to
explore tweaking models and seeing how
things can be extended. And so we offer
that as well through our custom node uh
feature. And because we are open source,
we do not only depend on the output of
the core team. We can trust the
community to let us know anything they'd
want us to work on.
and also make anything we do not have
the time to work on on our team.
Any comments? Comfy?
Uh well, I think uh yeah, I think we
haven't shown the interface yet. So,
yes, we have only shown one screenshot
of the interface at the very start. We
will uh show that off as well.
You want to do it? Just do it later.
Yeah.
All right. Story behind comei.
the quick stories that uh basically
confuse. I started as my own personal
project and then I and then uh
yeah and then which yeah I started in
January January 2023 and then
six months later I was hired at
stability AI. So I spent one year at
stability AI. they were using Comfy for
uh for more uh like experimentation
with uh internal experimentation with
the models and then I left stability AI
in June 2024 and then I joined up with
Yolan and Robin and we uh we made like
the comfy company and uh yeah that's uh
things have been going pretty well since
then. So,
yep. And this picture was taken on the
Yeah, we we went uh that that picture we
went on top of Mount Fuji uh which uh I
don't recommend. It's uh very very
difficult, but uh yeah, but we did it.
So, yeah, I lucked out and my flight to
Japan uh got rerouted to Alaska for 24
hours. So I landed in Tokyo 5 hours
before they were going to be waking up
to go to Mount Fuji. So I got to
Yeah. So you you missed the fun.
I missed the fun and then still got sick
for a week right afterwards.
Yeah.
Yeah.
All right. And like to know that
Comfyorg is indeed hiring. Uh you can
look at any opportunities on
Comfy.orgcareers.
Yeah. Yeah. We yeah, we're hiring for a
bunch of stuff. So, if you're interested
in joining us, if you're interested in
opensource uh generative AI, well,
that's uh maybe uh yeah, maybe we have a
a spot for you on our team. So,
you haven't checked out the website.
That is all for the official slides, but
now is the fun part of showing the UI
and taking any questions you may have.
Nice. I'm sure many on this side of the
room who are familiar with Comfy UI know
this standard uh galaxy bottle workflow.
Unfortunately, this spoils the results.
I'll just shake up the seed.
Anyone not familiar with Comfy UI? This
is all being locally rendered.
Yeah, but this is a very old model. This
is SD 1.5. Yes, this is so that's why
the results are not not very good.
Yes, this model was I think the one that
inspired your initial work on comfy UI
at the time.
Yeah. Well, fine-tunes of this model.
This is the base model which isn't very
good. But
yeah, this is
but it's very fast. So
it's very fast but it is ancient tech at
this point.
Yeah, it's almost three years old at
this point. Yeah,
ancient.
All right. And there's the UI like
you're you're you're looking at it.
Yeah. So, basically what Comfy does for
those who are not familiar, it kind of
splits the whole diffusion pipeline into
these different components. like a
stable diffusion model is a diffusion
model, a text encoder and a VAE, which
is why you have those three things
right here. So yeah model diffusion
model clip is the text encoder VA the VA
and then so have the sampler
VA decode and save image and that's
basically a basic uh diffusion model
pipeline
and what that lets you do is you can
check which models you have on here.
Not many.
Oh, maybe SDXL is
Yeah, that one should work for the
I can uh type those numbers in for you.
My uh rookie mistake of turning off my
num lock.
Let's see how quick my disc drive is.
Yeah, this is all running on the laptop.
That's why it's uh a bit slow, but
once it samples, we'll get there.
So, yeah. So, this does look a lot
better than that.
Yeah, this model is still also ancient.
I think this one's two years old at this
point.
This one's two years old.
Yep. We have more exciting workflows,
though. If we browse the templates, if
you want to go a little advanced,
we've got There we go. This will not run
because I do not have like 60 gigabytes
worth of models,
but here's what that workflow looks
like. Yeah, this is what a video
workflow looks like which you you can
see it's very similar from a from one of
the image workflows. It's just you still
have the
the sampling
node with different settings
and same VA code node which is kind of
hidden here
and yeah so
so this is this is the the one 2.1 model
that's probably the best open video
model at the moment and you can see the
the pipeline is still very similar to
even the first uh stable diffusion 1.5
model that was that we were presenting
earlier.
So yeah, but what that lets you
do the fact that you can uh you can go
and change things like say if I want to
uh
like this is one of a technique that uh
this is basically this node that I just
added. What it does is it u it's a what
I call a cfg trick. So it it will add
something to the uh to the sampling to
the cfg calculations of the sampling
code. So basically it's you can easily
write these nodes which uh which will
change. So you can go and just patch the
pipeline this way just by add just by
either writing your own nodes or using
nodes that already exist. And for anyone
unfamiliar with CFG, it is a
AI trick where you take the positive
prompt, you sample on that, you take the
negative prompt, in this case text and
watermark, you sample on that, and with
the magic of AI, you literally subtract
the results from each other, and that in
some way improves the image result.
Yeah, I think we can Yeah, I think we
can take Does anyone have any questions
about anything
like or anything in general related to
Comfy UI?
We have a question right here.
Yeah.
Uh yeah, those are basically those clip.
You know what clip is? Yeah. It's uh
basically the diffusion models they use
the text encoder part of the clip model
to
it's instead of so instead of passing
the text directly to the model they use
this uh a text encoder because that way
the model doesn't have to the diffusion
model doesn't have to learn like all the
to understand human language. it can
just learn the output embeddings of
whatever text encoder you use. So yeah,
so the this is uh basically the clip in
comfy UI represents the text encoder.
The reason it's named clip is because
before like on the stable diffusion
models they were only using clip as the
text encoder
but in later models it's more they start
later models started using different
text encoders that were not clips. So
the name I should yeah the name should
be changed but uh yeah so what this does
is it essentially what this note does is
it passes the text through the text
encoder and then the output would
essentially be the output embeddings of
or the last hidden the last hidden state
essentially of the text encoder and
that's usually well it depends it's
slightly different for every for every
model But essentially it's the most of
them it's the last hidden state or the
penultimate hidden state that is passed
to the diffusion model.
Yeah. Because this is a positive and
negative prompt. This is how the CF like
because the models how you sample most
of these diffusion models is with a
positive and a negative prompt and
that's a using CFG something called
classifier free guidance CFG
and what it basically the the idea is
that if you only sample with a positive
prompt so yeah if I put CFG G to one.
That's essentially just sampling with
the positive prompt. And you you can see
what happens when you you only sample
with a positive prompt. It's a
you can see that the image is wait this
is worse than well. Okay. It's because I
have this node. Well, this is worse than
it should be. But uh
Okay. Yeah. If I Yeah. If I sample with
just uh
just the posit you see that it's uh the
image is not very well defined.
It's very chaotic if you only So what
CFG does it's a trick because if you
think of all the possibilities of what
the model can generate it's kind if you
it's kind of a way to push for like the
CFG scale does when sampling it does
positive minus negative prompt and it's
a way to push the sampling very more
towards your positive and away from your
negative. So the higher the scale, the
more it will do that, which means you
get a more defined image.
I don't know if uh my explanation makes
sense, but uh
Yep.
Yep.
Yeah. the VA is because the what made
stable diffusion be ex work extremely
well
and uh yeah what what made stable
diffusion be extremely popular is the
fact that the the image generation
happens in compressed latent space. So
instead of doing it in pixel space on a
like let's say a 5 a 512 x 512 image in
pixel space that's that's a lot of
pixels or some earlier diffusion models
did that but they were pretty slow.
stable diffusion. It did this in a
latent space which uh for a stable
diffusion the VAE is 8x compressed on
every uh on every on the two two
dimensions. So yeah, so instead of uh
sampling a uh yeah, a 512* 512, you
would be sampling a 64* 64 image, which
is which is why these models are got so
popular because they were a lot more
efficient than what came before.
So yeah, so that's what the VA the VA is
just a Yeah, it's a VAE. In input is
like 512 * 512 * 3 channel and output
would be uh would be yeah 64 * 64 * 4
channel in the case of uh of this model.
Awesome. Thank you so much.
All right, we have a question right here
and I'll I'll give you the mic.
Thank you. So, um, Kofio is really in a
lot of the examples is focused on the
image generation as such, you know, kind
of all kind of cool plugins. Um, I
wonder if you have good suggestions or
ideas about evaluating the results kind
of like verifying or kind of like saying
this is good image or not a good image
uh to to kind of automate that workflow
as well.
Uh that's uh that's a difficult thing to
do usually because if uh it's the
problem where like how do you define a
good image
because uh yeah
that there's some problems with uh
because people's taste is very
subjective. So what is a good image for
one person might not be good image for
another person. So yeah, it's a it's a
problem they have. It's actually a big
problem with the like user people who do
who train these diffusion models like
user preference.
They uh when they when they actually add
the user preference data, their results
get a bit worse because users like
like the average user likes a certain
type of image which is not maybe might
not be what uh what most what most
people want. So it's uh yeah
but uh
any
models that you bring in or you kind of
have a prompt that looks at the image uh
like a multimodel but anyway if there's
not
yeah there's yeah I yeah we've had like
at least back when I was at stability we
did have some uh we did experiment with
some models that tried to just see oh
like get the output output the image
from the workflow get some kind of
rating from a model but uh it didn't
work that well so it's
okay good question
all right do we have any other questions
right now from anyone
raise your hand so I can see
Do you have another one? Awesome.
So, this is predominantly a workflow and
once you kind of like uh develop it, you
do it in the UI. Um any good tools
around then uh running this more
headless and kind of scaling this out
and maybe building this into an app for
kind of people using it.
Yeah, this is uh just uh yeah, this is
one thing that uh because well
is this what comfy UI is it's actually
you have this interface but you also
have a powerful backend behind it which
executes the workflows and right now
there's there's actually a lot of uh a
lot of different inference service for
these workflows and eventually we'll be
building our own. So, and yeah, and
there's there's already some uh a lot of
uh third-party services that I saw that
you can take your workflow make an app
out of it and uh yeah, so you can
already you can already do that but uh
just there's no just no official way of
doing it, but there might uh there might
be one in in the future. So,
okay, thanks for clarifying.
Thank you for the question.
All right, any questions? Because we'll
keep on talking about other stuff. There
are no more questions, so be prepared.
All righty. Uh, one of the more recent
additions to come for UI. For a long
time, we only supported open-source
local models. In the past month, we've
introduced API nodes, which for paid
credits allow you to generate remotely.
Um,
let's open up a template
we can do. There we go. One of the
models that recently came out was a
Black Forest Labs context model. uh
currently not out for open source usage
in terms of being able to run locally
but they have made the APIs available.
Yeah, eventually they're supposed to
release an open source version which uh
well we we already support they just
haven't haven't released it.
Yes, we are waiting for the green light.
Yeah.
And I would run this but I have no
internet connection and that's one of
the limitations of API notes. you need
to, you know, they're not ran locally.
Yeah. So,
there's some interesting
Yeah. So, we have u
Yeah. Yeah. We have a lot of different
uh so the models that so that we support
image, video,
yeah, 3D. So, we have a basic support
for like
Hunion 3D model which is uh basically
it's an interesting model. So it
basically outputs a voxal type uh
like the the 3D model all these output
is a kind of a voxal format and then you
and then so that's why in the workflow
there's uh yeah there's some uh
code to so but the problem with these
models since it's kind of it generates
some voxal format and then and you need
to use an algorithm to convert it to
mesh is that the mesh isn't very high
quality, but it's still uh pretty
impressive.
I do not have any of these models
coming.
Yeah.
And we're currently, I guess, not we
have local support for LLM.
Well, there there's a bunch of custom
nodes with local LM support. It's just
not a core comfy thing yet. It's just
we're more focused on uh on like image
and video and all these uh more visual
or we also support audio and audio model
now. So
yeah, it's not as good as some of the
proprietary models out there, but it's
uh yeah, it's pretty fun to play with.
And there were some more I think uh
audio models that came out.
Yeah. But those those are texttospech
models.
Gotcha.
Yeah. Those which we we may support.
We'll we'll have to see if uh because
they're they're already supported as
custom nodes but uh yeah before to
yeah it's just to integrate them in core
comfy there needs to be like a reason to
like if uh give them extra control or
some extra like extra knobs to turn or
else there's not much point.
I'm interested in any questions from
this side of the room that maybe wasn't
too familiar with Comfy at the start.
Uh, do you have any questions, comments,
inquiries?
All right, I will hand you the mic.
Sorry, it's me again. So does comfort UI
have the use case for the virtual tryon
where you know we upload the image of
the model uh the manqueen and the
garment the clothes so that it generate
the virtual trion images
yeah like for example the new flux
context model can can do that uh I think
so there yeah there's a few different
there's some opensource ways and there's
some uh some ways using uh the API nodes
But uh yeah, virtual trans it's
something that seems very popular. So
there are there are a bunch of workflows
for it.
Okay. So we can find it on the comfort
UI and try it out.
Uh yeah. Yeah. If you if you search you
can find uh you can probably easily find
a workflow for it. The only thing you
might uh it's just some of the it's just
that the field evolves so fast that uh
sometimes uh workflows you find might be
slightly outdated. So but if I was doing
that I would first try the new flux
context model since that seems to be uh
the best one for that. But uh
yeah
uh the name is new conf uh what's the
model name? new
uh flux concept
flex concept
context yeah I keep okay yeah flex sorry
flux context
cont
yeah context with a k
thank you thank you so much
and to also follow up on that um
right now yeah right now it's an API
node only but they're they should
release the uh the opensource version
soon so yeah so once that's once that's
released you'll be able to run it on
your on your on your machine with the
comfy UI.
Yeah. To follow up on virtual tryon,
this is actually something that people
have made workflows in the past year.
When we were in Japan, when we had a
meet and greet there, there were some
people who actually made workflows
specifically for that. Back then, there
weren't
some of the models like context now are
very good at a hey, change this one
thing. At the time, there weren't. So
the workflows you'd find probably have a
few dozen nodes basically finding using
a one model to find the masks of like
what to change then another model to
inpaint those masks of the actual thing
you want to change. Now the models are a
bit more uh advanced where you can just
say hey I want to edit this and it does
it. And you of course combine up the
masks as well. In case the model gets a
little
uh a little rowdy and tries to change
things you don't want, you can always
add masks to keep it contained.
Any more questions on this side of the
room?
So sorry I joined the session very late
late but um if you want to generate any
kind of image I think this allows us to
write a prompt and then it allows us to
generate image. Is that correct?
Yes.
Okay. So for example, if you want to
have a tool that automate
building multiple images based on let's
say character like if if I want to have
define a character and if if I want to
generate a stories based on the
characters does this allow it?
Yes. Well, you what you need is there's
a few different ways to because I assume
yeah, you want to generate a consistent
character
is depending on what you want. You can
either uh train a lora for your
character or use one of the newer model
like uh like the flux context model like
these uh like very recently there's all
these edit models that have what I call
edit models which are basically uh they
they got very inspired with what the 40
was doing.
So
which one do you suggest? What
which one do you suggest?
Uh right now the the best one is uh the
flex uh the yeah the flex uh context
model
but uh like I said it's only right now
it's only available through an API and
but uh should be open source soon and
then there's some other ones too but uh
at one yeah well what you can do with uh
with the the context text is just like
some you give it a reference image of a
character and you say, "Oh, make that
character do this." And it actually
keeps the character consistency
extremely well.
Just uh
so there is there is a way to uh
maintain character throughout the story
generation, right?
Yes. Yeah. Well, what you would do is
you would have a Yeah. First you
generate a your character of an image of
your character that you're happy with
and then you would uh you would pass it
to this model and say oh put this
character in this scene put this
character in that scene and then you
generate your image is based on this
reference image of the character.
Okay thank you.
And to follow up on that, one of the
advantages of a nodebased system is with
the way that is set up, all you can
currently edit in it are some of the
parameters and the text prompts, but you
could also apply the Lauras. Lauras are
uh low rank adaptations to the model.
Um, and because it's node based, you can
also mask the specific area each of
those low rank adaptations would apply
to. So let's say you have two Laura
strained, one for character A, one for
character B.
uh what our nodebased system allows is
to say hey in this area of the image I'd
like this Laura to be active maybe at
this strength you could even schedule it
in terms of that and on the other area
of an image you can have oh I want this
other character Laura to be active so if
even if you uh if like an all-in-one
model like context doesn't quite do what
you want there are multiple ways you can
sort of coersse these models to kind of
do it with a basic uh promptbased
system. There are of course limitations,
but because we are node based, you can
do, you know, there's two things for the
prompts there. You could set that up to
be 10 nodes, and some of those nodes
apply a specific Laura to a particular
image, sorry, to a particular area of an
image.
Do you also recommend Laura or uh the
other one? Um, if you don't have uh like
much experience in the space, I'd
recommend the context model mainly
because you just you just have to type
in the prompt and it does the work for
you. The other one, especially back
before the sort of, you know, edit via
text models existed was sort of a brute
force way of getting what you want, but
you could really get what you want
because you could train it on anything
you want. The models don't have to be
aware of what it is. And the the only
disadvantage is you need to have enough
training images. So like between 10 to
30 to actually get your subject to
appear the way you want them to. With
these newer edited models, you only to
give the one image.
No problem.
All right. Any questions here?
Or back on that area of the room? I can
walk.
All righty. What do you want to talk
about next?
Oh, well, yeah. Yeah. Well, we since we
mentioned Lauras, like Lauras are one of
the basically what they what they are is
a a patch on I call them a Yeah, they're
basically a patch on the model weights,
which is or a more efficient way to
train a concept or multiple concept in
in a in a model.
And yeah, right now we don't it's
basically just if you want to train a
model instead of training the full
model, you would train this small patch
on the model. And this allows you to
well you can train styles, specific
characters,
anything.
So yeah,
we can we can skip showing it off. This
was for the uh Japan presentation where
this this Laura is for for a anime
character that goes hard in Japan.
Probably doesn't go very hard at a AI
conference.
But this is how you would do it. You
would just chain the model there.
And these are
uh do I have any SDX? I do not.
Okay. This is for 1.5.
Yes. And uh they're for Japan.
I mean, we can still show them off, but
uh
All right, we can try.
Yeah.
Oh, and these would probably look very
poorly on these models, but we can give
it a shot.
Well, I used the anime one.
Okay, we can use an anime one.
Okay, that's the anime one.
Yeah, it works.
So, yeah, just
I mean, if you try that prompt, it's
probably not gonna
Yeah, we can uh we we can do that in a
bit. All right.
Okay.
What else would you like to talk about?
Uh yeah, can just try see. Yeah. Well,
we can press run and
I I don't know if we should I don't know
if we should press run.
Yeah. Well,
okay.
Yeah, we can. Yeah, this is a assignment
to do at home, I suppose.
But we have other models that we
support. Let's see. Yeah, apologies that
we do not have much live demos. Uh
uh there were some setup last minute in
terms of us attending the conference.
So,
but we are here.
Sorry about that.
Oh, here are some control net examples
where
can't show the inputs, but we can
actually I guess we can we can trust the
template system to kind of show what
that's about.
Yeah, control nets are just one of the
many ways to have more control of these
uh of the the models.
Yeah. So the examples here would be the
inputs that were used to actually
generate these images,
but those might be like control nets
might no longer be very useful because
now there's all these edit models that
are coming out. So yeah, it just means
that the space is uh is evolving. But uh
uh so here's a more advanced workflow
where it applies I believe different
prompts to different areas of the image.
Yeah, this is a different prompts to
different areas.
Yeah, we can actually make this one go
on the default SD 1.5 model. That one
will will work.
Okay. Ah, yes. This is the old way of
prompting things when the models kind of
had to really coers them.
We will fix the seed.
Okay. And let's see how the laptop
handles.
Yes.
See, assuming there's no loaded images,
this should just work.
Yeah, at least half the workflow should
work.
Yeah.
Yeah, this is a very old workflow, but
uh I think it's still works on even the
most recent models
and we can uh we can change the prompts.
Maybe it's more obvious, but I believe
the prompts are basically doing a
different time of day on some of these.
Yeah. Yeah, it's basically different
time of day on like if you go
Yeah. top is like night and bottom is
daytime.
Yeah. Just uh
Yeah. So, this is just one of many ways
you can get like more control. This is
just a way of applying different prompts
in different areas of the image. Like I
said, I think it it still works even on
the most recent models.
Yep. Yeah. Everything that basically
started from the foundation at Comfy set
up two years ago, most of those any of
those tricks or applications still apply
to newer models.
Yeah. Because they're general like
diffusion model tricks and we're still
using diffusion. So you Yeah. So that's
what makes Comfy nice is that if once if
a new diffusion model is implemented,
usually you can use all the old tricks
if you want. Some of them might not be
useful anymore, but you can still use
them.
Yeah, the models have also gotten bigger
and harder to run locally in some cases
on some hardware. So, uh, some of these
tricks would, you know, make things run
quite a bit slower. Um in the early days
of image generation a lot of the
improvements were with community
fine-tunes who would take you know vast
data sets and improve the base model.
You may have noticed I was a little
nervous running a model
a few minutes ago. The reason for that
that was one of those fine that was one
of the sort of days of back of community
fine tunes. uh the data sets they used
may not always produce uh the most uh
conference friendly content. Yeah,
there's there's some interesting things
that happen when a model is slightly
broken because since it's a diffusion
model, if it's slightly broken and
you're generating a like a a character,
the first like the first step might
produce a like a skin color blob, which
means it might converge to to a naked
person basically. So yeah.
Yeah. And given there are community fine
tunes that basically everyone trusted to
produce better quality images, those are
usually generations that you first
review and then show rather than press Q
and then uh
yeah but that's the power of running
things locally. You don't have any
problem. You can do whatever you want.
So
yeah newer models and bigger ones the
training sets are a bit more
constrained. So you you have the pro the
pro pros and cons of that.
It's just they're they're better. They
make less random mistakes.
Yeah. You can be more you can trust more
that when you put in a specific prompt
it will not hallucinate as much.
All right. So in terms of we mentioned
we are hiring. I believe we're looking
for positions on
well everything pretty much
back end front end
yeah core
cloud deployment
inference uh that cloud yeah just yeah
go look at our careers page and uh
yeah it's it's comfy.orgcreaters
org/creat.
And if you haven't tried the software,
go try it. You can just if you all you
need is a a decent GPU and you can run
it locally or you can use the API nodes
and Yeah.
Yeah. People have gotten some of the
early models to work on extremely old
GPUs like
Yeah.
80-y old GPS.
Yeah. Yeah. One of the strengths of com
is that pretty much any hardware well
any Nvidia hardware the model will
usually run. It might be extremely slow
but it will usually run.
So
yeah. So are there any final questions?
Oh right there.
Uh hold up. I'll give you the mic.
There's a process to this thing.
Thank you. Um, I've tried using Comfy
and I was just wondering like if you
could give us like a quick synopsis of
what do you think about Comfy versus the
alternatives that exist? Like why would
you sort of say Comfy is the one that
people should start with or stick to? I
have no idea like of the depth of it. So
just give me like a seminar of that
please.
Uh, Comfy is uh you should use it
because it's the it's the most basically
it's the most powerful one. So if you uh
like everyone who like it's basically
the the end game for for these these
types of interfaces. So there there's
nothing that gives you more control that
has more community support that has more
extensions.
So the only downside it has right now is
it's uh it's a bit difficult to get into
but we are working on that. So, thank
you.
Nodebased systems, especially if you're
not used to them at first, can be quite
intimidating. And as uh Comfy mentioned,
one of the greatest assets of Comfy UI
is that it is community extendable and
it is open source in that anything that
the core team may not be able to get to,
there probably exists a community
solution for that or to do something
like like we mentioned in the slide,
there are I believe 22,000
custom nodes within like 3,000 note
packs made by you know 3,000 separate
developers who are all passionate
If you go to other places, you will not
always have you know the certainty as oh
can I run this locally? Do I know all my
data safe in ter if you are in a for
example an enterprise setting data
security might be a big thing to avoid
becoming the next headline in terms of a
data leak or a ransomware attack. So
being being able to actually look at the
source code that's your thing or having
your team be able to look at the source
code. You can contribute any fixes. is
uh in terms of optimization and
performance we are pretty much
state-of-the-art uh comfy over there
when the new model comes out and he
hears that there is a way to run it
faster he implements it or one of us on
the team implements it so
um there's a discord channel that we
have for comfyorg we also as we post the
slides if you just Google comfy there
will be most likely thousands of YouTube
videos. Um there's even some people who
have taken uh they've seen the
opportunity of the difficulty of comfy
UI. Um and they are for example having
paid uh tutoring classes for it which is
a bit of a eye openener for us because
that says we should probably do a better
job onboarding users if uh people are
you know making money that way but there
should be a lot of resources out there
for you.
All right any other questions?
All right. Over there.
Is there currently a published product
roadmap?
Uh if you mean what we are currently um
well we haven't started really started
actually started yet but eventually
we'll have a solution to run these
workflows in the cloud.
And uh yeah, how exactly it's going to
work because we the the thing is before
doing that we want to fix there's a a
few issues we have to fix like the for
example we want to make it installing
and dealing with the custom node that
you install. We want to make that a lot
smoother, make uh the interface better.
add a Yeah, we're what we're going to do
is uh improve the interface
key. Well, the there's always going to
be the node interface, but uh we are
most likely going to add an other layer
on top of it where you can have a more
build a more traditional interface out
of your workflow graph. and that will
fit in with the well with the cloud
stuff that we're going to be doing
eventually. So yeah, so that's that's
the direction where we're going in. But
uh the thing is in this space is that
things change a lot. So a new model that
comes out tomorrow might uh might mean
we need to uh pivot a bit. So that's why
I'm not uh I'm not giving any promises.
So yeah,
because like the first thing that went
to my mind is we had the gentleman ask a
question about can we serve these
workflows up. So it's like if you can
access a workflow through an API, you
can have like a single power user
building out massive templates. Yeah.
That maintain like style and brand
guidelines or or story or character
design and then be like role-based
access control. You could have like just
a general user in there saying, "Hey, I
need to generate this workflow based on
these parameters. I can't touch anything
else in there." like is that is like
being more enterprise or team?
Yeah, team ready.
This is one of this is a direction we
are going into. So like having uh just
the the basics for that would be first a
good cloud inference service where you
can run workflows very well and have all
the custom nodes work and once we solve
that then all that other all that other
service becomes a lot easier. So yeah,
thank you.
Y and to follow up on that at the end of
the week, we will have a blog post about
some of the things we are working on um
for the because we are planning to allow
cloud services, but first as uh Comfy
said, we need to work out dependency
issues. So we'll have a bunch of
features being announced there. For
example, we'll have a subgraph option
where you can combine a bunch of nodes,
put it into one node, and you can double
click into it as like a separate
workflow. uh solving dependency issues
where custom nodes right now can request
different Python packages. Making sure
all of those could get either properly
isolated or have more ways for them to
report their compatibility because once
local becomes much better to run that
means our life trying to get this as a
cloud product will also become smoother.
Yeah, I think yeah we are out of time
now. So would uh would like to thank
everyone for coming. We uh Yeah. And I
hope you uh you learned something.
Yeah. Thank you for all the questions.
Greatly appreciated.
Yeah.
[Music]