CogVideoX

THUDM open video diffusion with strong prompt following.

Install Repository Website Compare

Fit.

Catalog snapshot

Platforms: Linux
Operating systems: Linux
Ram floor: 32 GB
Gpu: Required · 16 GB VRAM
Docker: No
Setup: Advanced
Deploy as: Local
Commercial use: Allowed

Apache 2.0. Read model cards for weight terms.

Project.

Fetched Sep 12, 2026¹

License: Apache 2.0
Stars: 13k¹
Forks: 1.3k¹
Open issues: 109¹
Language: Python¹
Last commit: Nov 4, 2025¹
Latest release: Jun 1, 2026
Tags: text-to-videodiffusiongpu

About.

CogVideoX is a research-to-local path for text-to-video. Expect CUDA, large weights, and a Python install. Better prompt adherence than older OSS stacks.

CogVideoX models · Diffusers path · I2V variants

Alternatives.

Nearby.

All Video AI

WWan2.1Alibaba’s open text-to-video and image-to-video stack.Compare
OOpen-SoraApache-2.0 research stack for training and running video diffusion on 24 GB cards.Compare
FFramePackLong local image-to-video with a low VRAM floor.Compare
LLTX-VideoLightricks open video model aimed at faster local clips.Compare
MMochiGenmo’s Apache-2.0 10B video model — permissive weights, heavy hardware.Compare