Run CogVideoX locally for free with Pinokio
Workflow

Run CogVideoX Locally for Free — One-Click Text-to-Video with Pinokio

June 2026 · 6 min read · CogVideoX · Text-to-Video · Pinokio · Local AI · Windows

CogVideoX is a free, open-source text-to-video model from Zhipu AI that generates smooth, high-quality 5-second clips from a simple text prompt — and you can run it entirely on your own machine, no cloud and no censorship. It isn't as polished as closed models like Sora, Kling, or Luma, but it was a major leap for open-source local video. Best of all, the install is genuinely one click thanks to Pinokio.

The CogVideoX models: 2B vs 5B

CogVideoX comes in two sizes, each suited to different hardware and licensing needs:

ModelBest forFull-precision VRAMLicense
CogVideoX-2BEntry-level — easy to run, great starting point~18 GBApache 2.0 (very permissive)
CogVideoX-5BBest quality, more detailed motion~26 GBCogVideoX license (more restrictive)
Low on VRAM? Those numbers are for the full-precision models, but the Pinokio build below lets you run CogVideoX on as little as 6 GB of VRAM by using the float16/optimized versions. You'll also want enough free disk space — the model download is 12 GB+.

Why Pinokio? One-click local AI

Pinokio is a free application that installs and runs open-source AI tools for you — think of it as a local program runner that handles all the messy dependencies automatically. It has a one-click installer for CogVideoX, which is by far the easiest way to get it running on Windows.

Requirement: this method needs an NVIDIA GPU.

Step-by-step: install CogVideoX with Pinokio

  1. Download Pinokio. Go to pinokio.computer, scroll to the download links, and grab the build for your OS (Windows, Mac, or Linux).
  2. Install and open Pinokio on your device.
  3. Open Discover. Click the Discover button in the top-right corner to see the full list of one-click open-source projects.
  4. Select CogVideo. It's one of the first options — click it, then click the Download button on its page.
  5. Install dependencies. You may get a popup about missing dependencies — just click Install at the bottom and Pinokio installs everything automatically. This can take a few minutes.
  6. Download the CogVideo repo. Once dependencies are in, a new download button appears for the CogVideo GitHub repo. Click it and let it download.
  7. Install the project. After the repo downloads, click the Install button that appears to install the project dependencies (another minute or two).
  8. Start the UI. If you see an error after the dependencies finish, hit Stop in the left sidebar, then Start — this relaunches the server and opens the CogVideo Gradio web UI right inside Pinokio.
Hit an error during the repo download? Make sure you're on the latest version of Pinokio, then simply restart the program — that resolves it in most cases.

Generating your first video

  1. Write a prompt in the prompt box. The model was trained on longer prompts, so more detail generally means better results.
  2. (Optional) Enhance prompt. The "enhance prompt" feature uses an OpenAI GPT model to expand your prompt — add your OpenAI API key in the Configure tab to enable it.
  3. Pick your model. Choose 5B or 2B, and the bfloat16 or float16 version (float16 is lighter on VRAM).
  4. Generate. Click Generate video. The first run downloads the model (12 GB+), so it takes longer. After that, generation typically takes 15 minutes or more depending on your specs — the model renders each frame individually.
  5. Watch it. When it's done, hit play to preview your clip right in the browser.
Bonus — video-to-video: the next tab over has a video-to-video feature. Upload a clip and have CogVideoX reimagine or improve it.

Looking for faster, newer local video?

CogVideoX was an early open-source breakthrough, but local video has moved fast since. If you want sharper output and faster generation on low VRAM today, check out these one-click setups:

Want it even simpler? The Local Lab builds one-click Windows installers for the newest local AI models — browse them in the store or get them all with Local Lab Pro.