[00:00] Today, I’ll show you how to generate AI&nbsp; videos for free on your own PC using ComfyUI.&nbsp;&nbsp; We'll install everything from scratch,&nbsp; generate videos from simple text prompts,&nbsp;&nbsp; animate existing images, and by the end of this&nbsp; video, you'll have everything running on your PC&nbsp;&nbsp;
[00:16] with no API keys, subscriptions, or usage credits.&nbsp; I'm Kevin, and let's dive in. First, head to the&nbsp;&nbsp; following website to install ComfyUI. You'll find&nbsp; a link right here at the bottom of the screen.&nbsp;&nbsp;
[00:28] ComfyUI is a free, open-source application that&nbsp; lets you run AI models directly on your own PC.&nbsp;&nbsp; That means once you install it, there are no per&nbsp; video charges. Today, we'll use it for AI video&nbsp;&nbsp;
[00:41] generation, but it also supports image generation,&nbsp; image editing, audio generation, and much more.&nbsp;&nbsp; On the website, you'll see options for desktop&nbsp; and cloud. We'll use the desktop version since&nbsp;&nbsp; everything runs on your own PC. If you don't have&nbsp; compatible hardware, the cloud version is a good&nbsp;&nbsp;
[00:57] alternative, but it requires a paid subscription.&nbsp; For this tutorial, I recommend using a Windows PC&nbsp;&nbsp; with an NVIDIA RTX graphics card, since that's the&nbsp; easiest and most reliable configuration to follow&nbsp;&nbsp; along with. Click Download Desktop, then click&nbsp; Download Desktop again to download the installer.&nbsp;&nbsp;
[01:14] Once the download finishes, run the installer.&nbsp; After installation completes, launch ComfyUI,&nbsp;&nbsp; and you'll see the following screen. For this&nbsp; tutorial, we'll select local so everything&nbsp;&nbsp; runs directly on your own computer. Down below,&nbsp; I'll agree to the terms, and then let's click on&nbsp;&nbsp;
[01:29] Continue. Next, let's give this installation a&nbsp; name. I'll set mine to ComfyUI. For most people,&nbsp;&nbsp; you can leave the remaining settings as is, and&nbsp; then down below, let's click on Continue. After&nbsp;&nbsp; it opens, you'll land here on the home screen.&nbsp; Over on the left-hand side, you'll see all the&nbsp;&nbsp;
[01:44] different types of AI content that you can create&nbsp; with ComfyUI, including images, videos, audio, 3D&nbsp;&nbsp; models, and here, even large language models. Now,&nbsp; today, we'll generate AI videos, so right up here,&nbsp;&nbsp;
[01:57] let's click on Video. Here, you'll see many of&nbsp; the different video models available in ComfyUI.&nbsp;&nbsp; Some run directly on your PC, while others use&nbsp; cloud services that require a paid subscription.&nbsp;&nbsp;
[02:09] Since we want to generate AI videos for free,&nbsp; let's filter this list to only show models that&nbsp;&nbsp; run on your own PC. Under the Runs On dropdown,&nbsp; let's click on that, and then select ComfyUI,&nbsp;&nbsp;
[02:21] and there, we see all the free models. Next,&nbsp; let's filter by task. I'll click on this dropdown,&nbsp;&nbsp; and if I scroll down the list, let's start with&nbsp; the basics of text to video. I'll select this,&nbsp;&nbsp; and now, you'll see several free models. Right up here, we have the LTX 2.3, WAN 2.2,&nbsp;&nbsp;
[02:36] Hunyuan, here we have Kandinsky, and SVD, lots of&nbsp; excellent models. For this tutorial, I'm going to&nbsp;&nbsp; use LTX 2.3, and the reason why is it's fast, it&nbsp; produces excellent results, and it also runs on a&nbsp;&nbsp;
[02:51] wide range of RTX graphics cards. Of course, you&nbsp; can always come back later and experiment with&nbsp;&nbsp; all these other models. So right over here, let's&nbsp; click on LTX. This drops us on the ComfyUI canvas.&nbsp;&nbsp; If you've never used ComfyUI before, this might&nbsp; look a little intimidating, but don't worry,&nbsp;&nbsp;
[03:07] we'll make sense of it. First, in the upper&nbsp; right-hand corner, you'll notice that ComfyUI&nbsp;&nbsp; shows a few errors. That's expected since we&nbsp; haven't downloaded the LTX 2.3 model yet. Right&nbsp;&nbsp; over here, let's click on Show Missing Models.&nbsp; In my case, there are five missing models. You'll&nbsp;&nbsp;
[03:24] also notice that they're fairly large. Together,&nbsp; they require about 40 gigabytes of storage,&nbsp;&nbsp; so make sure you have enough available disk space&nbsp; before continuing. Now right up here, I’ll click&nbsp;&nbsp; on Download All. ComfyUI will now automatically&nbsp; download all the files required for this workflow.&nbsp;&nbsp;
[03:40] Depending on your internet connection, it may&nbsp; take a little while, but you only need to download&nbsp;&nbsp; these models once. To track the progress of the&nbsp; downloads, you can click on this icon right up&nbsp;&nbsp; above. Once the download finishes, we're ready to&nbsp; generate our first AI video. At the center of the&nbsp;&nbsp;
[03:54] screen, you'll see the LTX 2.3 workflow. First,&nbsp; you'll see some helpful tips and information&nbsp;&nbsp; about the workflow. Next, you'll see two nodes.&nbsp; The first is where we'll configure and generate&nbsp;&nbsp;
[04:06] the video, and the second automatically saves the&nbsp; finished video. Let's start with the first node.&nbsp;&nbsp; Here, I'll zoom in so we can see it a little bit&nbsp; better. Although there are quite a few settings,&nbsp;&nbsp; you only need to change a handful to get started.&nbsp; At the top, enter a description of the video&nbsp;&nbsp;
[04:20] you'd like to generate. The more descriptive your&nbsp; prompt, the better the results will typically be.&nbsp;&nbsp; I'll enter in my prompt. I want a Kevin Cookie&nbsp; Company blimp flying over a city at golden hour.&nbsp;&nbsp; Below the prompt, you can adjust the width&nbsp; and height to control the resolution. Here,&nbsp;&nbsp;
[04:35] we have the duration to control how long the video&nbsp; is and the frame rates to control how smooth the&nbsp;&nbsp; motion appears. For this first example, I'll leave&nbsp; the default settings, but feel free to experiment&nbsp;&nbsp; with them later. Now, in the top right-hand&nbsp; corner, click on Run to generate the video.&nbsp;&nbsp;
[04:50] Depending on your graphics card, this may&nbsp; take a few minutes. And right down below,&nbsp;&nbsp; we could see that it's now finished. Let's preview&nbsp; how it turned out. The journey is just beginning.
[05:02] The aesthetic of the video is very nice, but&nbsp; it's a little bit more of a cross between a&nbsp;&nbsp; hot air balloon and a blimp. Of course, I could&nbsp; always go back and make my prompt more specific.&nbsp;&nbsp; ComfyUI automatically saves the generated video&nbsp; for you. To view all of your generated content,&nbsp;&nbsp;
[05:17] over on the left-hand side, click on Assets. And&nbsp; from here, you could preview your videos, and if&nbsp;&nbsp; you right-click, you could save it elsewhere on&nbsp; your PC, or down below, you could also delete it.&nbsp;&nbsp; I'll click out of Assets. In addition to&nbsp; generating videos from text, ComfyUI can also&nbsp;&nbsp;
[05:32] animate existing images. Let's now head back to&nbsp; the templates gallery. Down below, I'll click on&nbsp;&nbsp; Templates. Let's go back to the tasks dropdown.&nbsp; And over here, let's deselect Text to Video,&nbsp;&nbsp; and if we scroll up just a little bit, here&nbsp; we'll find the image to video. I'll select that.&nbsp;&nbsp;
[05:47] And right over here in the top left-hand corner,&nbsp; we have LTX 2.3. Let's select that since we've&nbsp;&nbsp; already downloaded those models. Now, you'll&nbsp; notice that this workflow looks very similar&nbsp;&nbsp; to where we just were, except now we can start&nbsp; with an image. So over here, I'll drag and drop&nbsp;&nbsp;
[06:03] in an image of the Kevin Cookie Company blimp,&nbsp; or at least what I think looks more like a blimp.&nbsp;&nbsp; Then right over here, we could enter in&nbsp; a prompt describing the motion that you&nbsp;&nbsp; would like to see. So over here, I'll type&nbsp; in the prompt. Now, for this first example,&nbsp;&nbsp;
[06:16] I'll leave all the remaining settings as their&nbsp; defaults. And in the top right-hand corner,&nbsp;&nbsp; just like we did before, let's click on Run.&nbsp; Down below, let's preview how this turned out. We've only scratched the surface of what ComfyUI&nbsp; can do. In addition to Text to Video and Image&nbsp;&nbsp;
[06:35] to Video, you'll also find workflows for video&nbsp; editing, camera control, inpainting, upscaling,&nbsp;&nbsp; and many other AI tasks. You'll also notice that&nbsp; ComfyUI supports many different AI video models.&nbsp;&nbsp; Today, we used the LTX 2.3, but you can also&nbsp; experiment with other models to compare the&nbsp;&nbsp;
[06:51] results and find the one that works the best for&nbsp; your projects. As you become more comfortable&nbsp;&nbsp; with ComfyUI, you'll also be able to customize&nbsp; these workflows, combine different models, and&nbsp;&nbsp;
[07:03] create even more advanced AI videos. And that's&nbsp; how you can generate AI videos for free using&nbsp;&nbsp; ComfyUI. If you have any questions, or if there's&nbsp; another ComfyUI workflow you'd like me to cover,&nbsp;&nbsp;
[07:15] let me know in the comments right down&nbsp; below. I'll see you in the next video.