Skip to main content

Z.aiVideo model

CogVideoX1.5-5B I2V

Clip lengthRank 47 of 63

6slongest single cliphigher is better

PopularityRank 392 of 875

33out of 100first value

Summary

CogVideoX1.5-5B I2V is a video model from Z.ai. CogVideoX1.5-5B I2V is an image-to-video checkpoint with separately published weights.

What CogVideoX1.5-5B I2V can do

“n/a” means the provider does not state it or we have not sourced it yet. That is not a “no”.

Text to videon/a
Image to videoyesSource
Referencesn/a
Audion/a
Runs locallyyesSource
Extendn/a
Start and end framen/a
Max. resolutionbis 1360 px lange Seite; kurze Seite mindestens 768 pxSource

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 98 models

LTX-2.570
MiniMax H366
Muse Video62
Sora 259
Wan 2.1 T2V 14B54
Wan 2.1 T2V 1.3B54
Runway Gen-4.553
Hy-Nomas53
Wan 2.1 I2V 14B53
Veo 3.150
Wan 2.2 TI2V 5B46
FLUX.3 Video45
LTX-2 19B45
Open-Sora 2.044
Wan 2.2 I2V A14B43
Gemini Omni Flash43
SkyReels V2 T2V 14B42
Grok Imagine Video42
Mochi 1 Preview39
CogVideoX1.5-5B I2V33

As of November 2026 · Source: gradually.ai popularity index

Over time

First value from November 5, 2026. The timeline appears from the second week.

CogVideoX1.5-5B I2V compared

Compare with another model

All specifications

Architecture

Parameters
5B
Source: Parameters

Input and output

Maximum resolution
bis 1360 px lange Seite; kurze Seite mindestens 768 px
Source: Maximum resolution
Maximum duration
6 s
Source: Maximum duration

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Weights
Open weights
Source: Weights
Access
Local
Source: Access
Release
CogVideoX1.5-5B-I2V was released on November 8, 2024.
Source: Release
Model license
The weights use the separate CogVideoX LICENSE. Apache 2.0 for the code is not the model license.
Source: Model license

Further details

Checkpoint
Canonical current Hugging Face ID: zai-org/CogVideoX1.5-5B-I2V. The SAT repository zai-org/CogVideoX1.5-5B-SAT contains separate transformer_i2v and transformer_t2v modules.
Source: Checkpoint
Input mode
Image-to-video checkpoint with separately published weights.
Source: Input mode
Generation limits
The model matrix lists a minimum of 768 px and maximum of 1360 px for the long side, dimensions divisible by 16, 6 seconds, and 8 frames per second.
Source: Generation limits

Frequently asked questions about CogVideoX1.5-5B I2V

How long can a video with CogVideoX1.5-5B I2V be?

Up to 6 seconds in one go. Resolution: bis 1360 px lange Seite; kurze Seite mindestens 768 px.

According to Z.ai

Longest clip
6s
Resolution
bis 1360 px lange Seite; kurze Seite mindestens 768 px
Open weights
yes

Sources and data date

Show all 9 sources
TypeEvidence and data date
Additional sourceZ.ai (retrieved November 1, 2026) · Z.ai · Editorial description reviewed November 1, 2026
Additional sourceZ.ai (retrieved November 1, 2026)12
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0