Question 1

What is Cogvideox Vae?

Accepted Answer

Cogvideox Vae is a VAE (Variational Autoencoder) that encodes and decodes latent representations. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Cogvideox Vae with ControlNets, LoRAs, upscalers, and custom nodes to build any pipeline you need. There are 1 community workflow templates using Cogvideox Vae on Comfy Hub, ready to load and customize.

Question 2

How do I use Cogvideox Vae in ComfyUI?

Accepted Answer

Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/utility/void-video-inpainting. You can also load any of the 1 community workflow templates that use Cogvideox Vae directly in ComfyUI.

Question 3

How many ComfyUI workflows use Cogvideox Vae?

Accepted Answer

There are 1 community workflow templates that use Cogvideox Vae on Comfy Hub. Each template is ready to run in ComfyUI and can be customized to suit your project.

Question 4

Is Cogvideox Vae free to use in ComfyUI?

Accepted Answer

ComfyUI is free and open source. Cogvideox Vae weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.