CogVideoX
CogVideoX is Zhipu AI's open text-to-video and image-to-video model family, released in 2B and 5B sizes with a 3D causal VAE and an expert transformer that fuses text and video in a single stream. It generates six-second 720x480 clips at 8fps, the 2B version is Apache 2.0, and with quantisation and offloading it runs on a single consumer GPU.
- Type
- Video
- Weights
- Open
- Downloads
- 6
- License
- mit
- Library
- diffusers
Model hub
aguerrero90/cogvideox
- Repo
- aguerrero90/cogvideox
- Access
- Public
Technical tags and languages
More from Z.ai
11
-
2.9k DL
ChatGLM 6B
Text
Short description (max 500 chars): ChatGLM-6B is an open bilingual Chinese-English conversational language mo…
-
GLM 4 32B 0414 128k
Text
A 32B-parameter GLM-4 checkpoint with 128k context. Strong general reasoning and coding, tool and function ca…
-
106k DL
GLM 4.5
Text
GLM 4.5 is Zhipu AI’s flagship general-purpose model, tuned for strong reasoning, coding, and bilingual Chine…
-
GLM 4.5 Air X
Text
A balanced GLM 4.5 profile focused on efficiency. Strong instruction following, long context, reliable tool c…
-
GLM 4.5 Flash
Text
A speed-tuned GLM 4.5 for low-latency assistants. Long context, tool and function calling, streaming, and cle…
-
GLM 4.5 X
Text
The higher-accuracy GLM 4.5 tier for harder reasoning and coding. Very long context, precise tool calling, an…
-
46k DL
GLM 4.5V
Multimodal
GLM-4.5V is a 106B parameter (12B active) MoE-based visual reasoning model supporting image, video, document,…
-
19k DL
GLM 4.6
Text
GLM 4.6 is Zhipu AI’s newest general-purpose model, improving on 4.5 with steadier reasoning, stronger coding…
About Z.ai
1
Z.ai develops the GLM family of foundation models and related generative-AI applications and developer services.