Hermes + Comfy UI is Insane (FREE)!

Hermes AI Agent just got a new skill and it makes it 10 times more powerful. You can now generate AI images, video and audio free from your computer. No subscriptions, no API costs, no complicated setup. Hermes AI Agent handles it all for you and we're talking about photo, realistic images, text to video, object swaps, etc.

And I'm going to show you exactly how it works step by step with Comfy UI today. This is all running locally on your machine or you can host it in the cloud as well. I'll show you both options and which one is right for you. And this is all triggered by using and asking Hermes AI Agent.

And the wildest part is, you can do this from your phone. So Flux, for example, can be running on your computer, Hermes can be connected, you can send a prompt and it generates the images and sends it straight back to you. This is a free local AI creative studio and Hermes Agent just unlocked it with one update. I want to show you exactly how it works right now.

So today we are going to be testing out Comfy UI, which is a powerful way to generate UI and Hermes can now automate it directly for you. So it's a new skill with Hermes that just makes it 10 times more powerful. I'm going to load this in now. You can see here, for example, this is the skill itself.

If we want to get this installed, what we can actually do here is we have to update Hermes, all right. So if we go to a new tab in terminal, you can press command and T to open up, press Hermes update inside the terminal. That's now going to update to the latest version of Hermes. And once we've done that, we can start using this new skill.

All right, so we've now updated as you can see. And now if we load up Hermes again, we can start using the new skill right now. If you want to know, okay, what does the skill do, how does it work, et cetera, you can see the full skill MD file here for Comfy UI. So it can generate images, it can generate video and it can generate audio directly with Comfy UI and Hermes.

So let's get straight into this. We're going to say, okay, I'm just going to switch the model actually first as well. And we're just going to check this works. So I'm going to paste in the skill MD file and just say, can use Comfy UI skill like so.

For some reason, just be careful when I updated it switched to Gemma 4, which doesn't make any sense. So that's why I have to switch the model right there. Just be aware of that. And you can see it's now loading the Comfy UI skill and we just need to install this.

Now we've got two options here. We can do a local install or a cloud install. I'm going to go with a local one and that's beginning to install now. So if you're wondering, okay, what is Comfy UI, how does it work, et cetera.

So it's a powerful visual AI engine application, right? So it lets you design stable diffusion pipelines using graphs, nodes, flow charts, et cetera. You can see an example of that right here. And it's an open source project.

You can run it on Apple Mac, Silicon, as you can see right here. And Hermes should just set this all up for us as well. So this is now running locally with Comfy UI, like you can see. So we can actually browse between what we can set up, how we can use it, et cetera.

Now there's a bunch of templates here, but basically what this means is that we are running Comfy UI locally with Hermes agents. So Hermes has set up, installed it, got it running locally. And it's actually given us some options on the models we can use to generate images and videos locally too. Now you can see there's three different options right here.

There's a super lightweight one, there's a general purpose one, and there's a higher quality one, right? And Flux is obviously one of the best local image models if you want to use that. So it's up to you what you want to use and how good your setup is. The other option is, of course, if you don't want to run this locally, then you could use it with Comfy Cloud.

Obviously you would need a API key for Comfy Cloud if you're going to link those together, but that's an option too. That means that basically all the models are hosted in the cloud and you just get access to them straight away. So those are two different options right here. This is currently downloading Flux for us and setting it up.

Now if we go full screen on Comfy UI, let me explain what we've got here and how it works. So if we have a look here, for example, we've got all these different templates. Now if we clear this, there's so much you can do with this. So for example, you've got like reference video, image to video, text to video, etc.

All these different styles of videos and images that you can create. It's pretty much endless. There's also a popular section so you can filter between those. And bear in mind, you can operate this all from your phone pretty much with Hermes as well.

Now if you go to utility as well, there's some interesting stuff here. So like different frames and that sort of thing, image segmentation, etc. Upscaling, removing image backgrounds, etc. So it's really good for image generation, video generation, editing images, and that sort of thing too.

Now you can also generate like really nice workflows too, which I'll come on to in a second. And then if you're wondering, okay, what can you do with the local models? So if we just filter down to Flux and we pull these up as examples here, we can see the local setup we can create using Flux, right? So for example, like image editing, generating photorealistic images.

We've got, for example, image object swaps. So we can change objects inside the image. And if you set up Flux and start running it locally, bear in mind it's only 12 gigabytes, which is not big at all, right? That's not a huge amount.

Then you can run this locally from your phone, right? So we can have, for example, Flux running locally with Hermes. Hermes is controlling Comfy UI. And then we can generate images using the power of Comfy UI and Hermes from our phone when we're out and about and that sort of thing.

And it's a free model, right? Now also if you go over here, you've got these different options on the sidebar. So for example, you've got media assets. So this is basically stuff that you've created or imported.

So you can look for your history here. Then you've got the nodes. So you've got image, video, audio, et cetera, text, and 3D nodes. You can switch between the model library and see what's happening here.

And in here, you can actually see a full workflow of what, an example workflow of what you could create and how you could create it, et cetera. And then you can just run it. It feels a little bit like NSN, actually, when you look at that, it feels like NSN. And then over here, you've got the workflow so you can create new workflows.

You can refresh them. You can switch between like graph and that sort of thing. And you can also explore any sort of workflows you've created previously. Then you've got the template section.

So if you're using a specific model or you're wondering, okay, what can I do with certain models? Well, you can switch between them here. For example, there's even options for 11 labs. So if we clear all and then we fill it down to 11 labs, you can see, for example, you could set up like text-to-speech or you could generate UGC video with text-to-speech and 11 labs and that sort of thing, which is pretty cool.

Then you've got your terminal set up here. So you can actually speak inside terminal here. You've got a bunch of keyboard shortcuts and then the settings, just like different customizations. You can go really deep on the customizations as you can see here, but I don't think 99% of people are going to do that.

I think it's just useful for you to set up the basic models and then run it from there. And you can see here that the Hermes has done that for us. Also, if you have any problems, like I had a couple of problems or a couple of areas where it's a bit slow setting up, so you can just ask Hermes, okay, how can I set it up or how can I fix this or that sort of thing. And it will just guide you through the process here.

It also looks at your current setup and is like, right, okay, based on your setup, here's what I recommend for you. So if you're not sure whether you should be running local cloud models, just ask Hermes. It will look at your local setup, as long as you're running this locally, and then give you a couple of options like you can see, right. So thanks so much for watching.

If you want to get more training on stuff like Hermes, AI Agents like OpenCLR, et cetera, you can get that inside the AI Profitable. This is my community that's focused on helping you save time and scale with AI automation. You can ask questions inside the community and I do weekly updates here too. You can also jump on the weekly coaching calls.

We have four weekly coaching calls. You can share your screen, ask questions about your setup, meet other people using AI Agents too. We drop new advanced daily tutorials inside here, as you can see as well, with full step-by-step guides. More is updated in this.

And then also we have a full course on OpenCLR and another two-hour course on Hermes. Then inside the classroom, you see all my best trainings and you can connect with me personally here too. Inside the map, you can meet people in your local city using AI and AI Agents, which is great for getting to know people. And then this is available, link in the comments description or go to the AIprofitable.com to get access.

Thanks for watching.