Skip to main content

Skywork AIVideo model

SkyReels V2 I2V 1.3B

Clip lengthn/a

n/alongest single cliphigher is better

PopularityRank 545 of 875

24out of 100first value

Summary

SkyReels V2 I2V 1.3B is a video model from Skywork AI. SkyReels V2 I2V 1.3B supports image-to-video with a text prompt and a supplied first frame.

What SkyReels V2 I2V 1.3B 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
AudionoSource
Runs locallyyesSource
Extendn/a
Start and end framen/a
Max. resolution540pSource

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

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

Over time

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

SkyReels V2 I2V 1.3B compared

Compare with another model

All specifications

Architecture

Parameters
1.3B
Source: Parameters
Checkpoint
Official 1.3B I2V checkpoint `Skywork/SkyReels-V2-I2V-1.3B-540P`; it is separate from T2V 14B and DF 1.3B.
Source: Checkpoint

Input and output

Maximum resolution
540p
Source: Maximum resolution
Native audio
No
Source: Native audio

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
Skywork released the model weights on April 21, 2025.
Source: Release

Further details

Input mode
Image-to-video with a text prompt and supplied first frame.
Source: Input mode
Documented output
The vendor table lists 540p and a recommended sequence length of 97 frames. It does not define a maximum duration.
Source: Documented output