Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
CogVideoX thumbnail

CogVideoX

by ModelsLab

Generates coherent text-to-video content at 720x480 resolution, 8 FPS, with up to 6-second clips, leveraging diffusion transformers and efficient 3D variational autoencoding for smooth motion and semantic alignment.

cogvideox
Open Source ModelUnlimited UsageLLMs.txt
API PlaygroundAPI Documentation

Input

Per Video generation will cost 0.0047$
For premium plan Video generation will cost 0.00$ i.e Free.

Output

Idle

Unknown content type

CogVideoX Readme

Generates coherent text-to-video content at 720x480 resolution, 8 FPS, with up to 6-second clips, leveraging diffusion transformers and efficient 3D variational autoencoding for smooth motion and semantic alignment.