Free AI Video Generator on Your PC (No Subscriptions, No Limits)

0:00Hey everyone, Kevin here. Today, we're going to look at how you can generate AI videos for free,

0:06directly on your PC. No usage limits, no subscriptions, and everything stays private. We'll

0:13walk through how to run some of the most popular open-source AI video models, including LTX-2 and

0:20Wan, and it's not just video. These models can also generate audio and narration. That's it,

0:27dad's lost it. And we've lost dad. Stop being so dramatic, Jess. He's just having fun. Wheeeew!

0:37That's an example clip that I generated on my computer. Pretty impressive. Let's get

0:42started. First off, you'll want to check your system requirements, since this is

0:46running locally on your computer. Generating AI video is resource intensive, but even lower end

0:54machines can handle it surprisingly well. You'll want a computer with a dedicated graphics card,

1:00ideally an NVIDIA GPU. You can get this running with six to eight gigabytes of VRAM,

1:06but more VRAM will give you better performance and also longer clips. To check how much VRAM you have

1:13on a Windows PC, press Control-Shift-Escape to open up Task Manager. Over on the left-hand side,

1:19click on Performance, and then click on GPU. Right down here, you'll see Dedicated GPU Memory. That's

1:25the number that matters. Here, you'll see that I have 16 gigabytes. Again, you'll want at least six

1:31gigabytes to get started. To make this easy, we're going to use a tool called Pinokio. If you've ever

1:37installed AI tools before and different models, you know that it could get complicated fast. You

1:43have to worry about different Python versions, CUDA, and all of these different dependencies.

1:48Pinokio handles all of that for you. The best way to think of it is, it's essentially

1:53a one-click installer for AI tools, similar to Steam with games. To get Pinokio, head to the

1:59following website. You'll find a link right at the bottom of the screen. Once you land on this page,

2:04click on the button that says Download. You can install Pinokio on Mac, Linux,

2:09and also Windows. In my case, I'm using Windows, so I'll select this and then click on Download

2:14for Windows. Go ahead and download it and then run through the install process. During the install,

2:18you'll be prompted to choose a name for the project. I'm good with the default, so over here,

2:23let's click on Download. This pops up in Install Screen. Let's click on Install. The first install

2:27can take a few minutes since it's downloading all of the models and all of the dependencies,

2:32but the good news is you only have to do this once. Once you've finished installing Pinokio,

2:37you'll land here on the main welcome screen. You'll see a button that says Discover. Let's

2:41click on this. This shows you a list of all the different verified scripts that you can install.

2:46Now, I think it's worth browsing through here. You'll find things like image generators,

2:50voice cloning tools, text-to-speech, and a whole lot more. For this video, we're going

2:56to use a script called Wan2GP. Right up on top, you can type that in Wan2GP. You'll find the text

3:02at the bottom of the screen as well. Right over here, I see the option, so let's click on that.

3:07This gives us a simple interface for generating AI video, and more importantly, lets us run multiple

3:13video models in one place, including Wan, LTX, and others. Right over here, let's click on

3:19this Install button. The nice thing, it's just a one-click install with Pinokio. I’ll click here

3:23and then let it run. On the next screen, we could see all the different dependencies that we need to

3:28install. If we weren't using Pinokio, we'd have to go through and manually install all of these,

3:33but again, Pinokio makes this a lot easier. At the very bottom, let's click on Install. Once

3:38the install finishes, you'll see Wan2GP inside Pinokio. To launch it, you simply click on it,

3:44and here on the top bar, you see the option to start it. Let's click on that icon. That might've

3:50taken a little bit of time, but once that wraps up and everything loads, you'll be taken to a simple

3:54web interface. Right up on top, you can see that we're currently in the web UI. Right down below,

4:00we have a number of different tabs. I'm currently in the Video Generator tab because we want to

4:04generate videos. Now, this is one of the cool parts. Right here, we have a dropdown where you

4:10can choose the AI video model that you want to run on your PC, and we have some really popular

4:14options. Right here, we have Wan2.2, and right down below, one of my favorites, we have LTX-2.

4:22In this video, I'm going to use the LTX-2 model. This is a relatively new AI video model, and one

4:29of the things that makes it interesting is that it can also generate sound or music alongside the

4:34video output. Let's select LTX-2. All in all, I've been very impressed by this model. In fact, some

4:40of the output is very similar to what you would get from Google's Veo 3 or even OpenAI's Sora 2.

4:47Up here in this dropdown, you can see how many parameters the model has. In this case,

4:52it's a 19 billion parameter model, which practically means it takes

4:57about 35 to 40 gigabytes of disk space just for the model weights.

5:01Next to that, we have another dropdown, and we have two different options. We have default

5:06and also distilled. So, what's the difference and which one should you choose? The distilled

5:10version is roughly half the size of the full model, so that means it's about 20 gigabytes,

5:15and it's also much more practical to run on consumer GPUs. Now, I have a consumer GPU,

5:20so I'm going to select that, and I'm also assuming that most viewers will also have a consumer GPU.

5:25Now, I found that the quality difference is fairly small, but performance and stability are

5:30noticeably better, so for that reason, I'm going with distilled. Before we actually run this model,

5:35let's make a few changes to the configuration. Up on the top tabs, let's click on configuration,

5:41and then we have another row of tabs. Let's click on performance, and then scroll down just a little

5:46bit, and here we'll see the memory profile, and you have a few different options. Take a look

5:51through these, and then choose the one that most closely matches your PC. Now, my PC has a lot of

5:56RAM, and I'm also close to 12 gigabytes of VRAM, so I'm going to choose profile two. Once you make

6:03your selection there, right up on top, click back into the video generator. If we look down just a

6:08little bit, there are a few different ways that we could run this model. We could run it with

6:11a text prompt only. That's where we use text to describe what we want the AI video to look like,

6:18but we also have a few other options. You can also provide an image and text that describes

6:23what you want the video to look like. In fact, you can even provide an end image or where the video

6:28should end, and right over here, you can even continue a video, so you can provide a video,

6:34and then it'll extend it. In a little bit, we'll look at some of these different options, but for

6:38now, let's start with a text prompt only. I'll click on this. If we scroll down a little bit,

6:42you'll see the prompt field, and this is where we describe what we want the AI video to look like,

6:48and here, they've provided just a sample prompt that you could use, and in fact,

6:52if you just want to test it out, you could use this just as is, or you could delete it,

6:56and you could type in your own prompt. So here, I'll type in my own. Now, here's one

7:00of the cool things. You could even call out if you want narration in your video. So here, I say,

7:05"She says," and then I have a line that I want one of the characters to say. That's one of the

7:09great things about this model. It produces both sound and also narration. As with most AI models,

7:15the more descriptive your prompt is, the better the results tend to be. If you want help refining

7:21prompts, tools like ChatGPT or Gemini can be great for brainstorming or adding detail. Underneath

7:26the prompt field, you can choose the quality level all the way up to 1080p, and next to that, you can

7:32also choose the aspect ratio. I recommend starting with a lower resolution. Lower resolutions render

7:38faster and are also easier on your system. And of course, you can always increase the quality later

7:44once you've confirmed that everything is running smoothly. Here in the aspect ratio dropdown,

7:49if you want a vertical video, say for TikTok, you could go with this nine by 16. If you want

7:54a horizontal video or what you'd traditionally find on YouTube, you could select 16 by nine. I'll

7:59select 16 by nine. Right down here, you can set the duration for your video. Now, the default,

8:04it sets at 24 frames per second. Now, with this slider, you could go all the way up to about 30

8:09seconds of video generation. Of course, that'll take longer to generate. Or here, you could go all

8:14the way down to just under a frame. Now, I'm going to go with about, let's say about 10 seconds. So,

8:20it turns out 10 seconds is about 240 frames. So here, I'll enter in 240. Once you finish

8:26entering your prompt and configuring all the different settings, over on the right-hand side,

8:30you can click on Generate. Now, here's one of the cool things. Once you click on Generate,

8:35you can go back over to the left-hand side. You could enter in additional prompts. You could

8:39configure the different settings and then you could click on Generate again and it'll add the

8:43next one to a queue. So as soon as your first video finishes generating, it'll automatically

8:47jump to the next video that it has queued up. Right above, I'll click on Generate. If you

8:52scroll up, in the top right-hand corner, you can check the progress of the AI video generation.

8:57And it looks like it finished generating the video in about one minute and 55 seconds. Now,

9:02I found that when you run a prompt the first time, it usually takes a little bit longer because the

9:07model needs to load into memory. And after that, generation speeds up significantly. In fact, I've

9:12gotten video generation down to about 30 seconds a clip, not bad. Now, right here, we can see a

9:17preview of the video file that it generated. Let's preview how this turned out. We need the brand to

9:22feel more authentic. Mm-hmm. The cookies will tell us when the time is right. Should we reschedule?

9:30Not bad at all for a first video and it even included some dialogue. Of course, if you want to

9:35make some modifications to it, or maybe you want to refine the video, over on the left-hand side,

9:39you could refine your prompt and then you could generate again. And a cool trick, you could even

9:44run multiple variations of the same prompt. If you scroll down just a little bit, they have something

9:50called Advanced Mode. And when you toggle that on and you scroll down just a little bit, you could

9:55choose the number of generated videos per prompt. So, as an example, you could type your prompt and

10:00maybe you'd like to see four different possible outcomes from that prompt. So, another option that

10:05you have. Here, I'll move that back down to one. Along with generating an AI video from text, you

10:10can also start from an image, and this is really cool. Right up on top, let's close out of Advanced

10:15Mode and right at the top, let's select Start Video with Image. Let's scroll down a little bit

10:20and over here we can drop in media. Here, I have a nice photo. I'm going to drop this and I generated

10:25this with AI, but I would love to see it animated. You could even upload multiple images. Now,

10:31right down below, let's scroll down and here we have the prompt field again. I'll remove all the

10:36texts that I had from my previous prompt, and here I'll type in a new prompt. The person continues

10:40walking towards the castle as the snow continues to fall. So, let's see how that turns out. Here,

10:45I could choose the quality and the aspect ratio. Now, I think all this looks good, so over on

10:50the right-hand side, I'll click on Generate. Right up on top, let's see how it turned out.

11:02That's cool. Now, right down below, you'll see all the output that you've generated so far,

11:06and you'll only see a few different items down here. So, you might be wondering, well,

11:10how do you view all of the output that you've generated? Up at the very top, there's a tab that

11:15shows the total space that Wan2GP consumes. Let's click on that and that'll open up File Explorer.

11:22Right in here, you'll see that we're in the wan.git folder, basically the project

11:26folder. Right over here, there's a folder titled App. Let's click on that. And if we look down,

11:31there's one titled Outputs, and here you can see all the different AI video that

11:35you've generated. What's so impressive here is that this all runs locally. No subscriptions,

11:41no usage limits, and you stay in control of your files and your hardware. Let me

11:45know what you think in the comments. Thanks for watching and please consider subscribing.