CogVideoX-2B

Video

VideoTHUDM

Description

Faster, lighter video model for quick iterations

CogVideoX. Video generation from THUDM/Tsinghua

Tags

videotext-to-videofastlocal

Capabilities

Vendor: THUDM
Family: CogVideoX
Type: Video
Model ID
Tasks: Text to video

Inputs

Prompt: Required

Outputs

Duration: 5 seconds, 10 seconds (default 5)
Frame rate: 8, 16; default 8
Resolution: 720p
Aspect ratios: 16:9, 9:16, 1:1

The catalog has no structured price for this model.

Compare prices on modelpricetrack.com

Where to run it

Tasks and limits are per catalog row. A provider may offer only some of them.

Local GPUAPI

Video

Prices

Only sentences in the catalog that state an amount and a unit.

The catalog has no structured price for this model.