SkyReels-V2

Closed weights Kunlun Inc. 14B parameters April 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Kunlun Inc.
Organisation type
Industry
Country
China
Published
21 April 2025
Authors
Guibin Chen, Dixuan Lin, Jiangping Yang, Chunze Lin, Junchen Zhu, Mingyuan Fan, Hao Zhang, Sheng Chen, Zheng Chen, Chengcheng Ma, Weiming Xiong, Wei Wang, Nuo Pang, Kang Kang, Zhiheng Xu, Yuzhe Jin, Yupeng Liang, Yubing Song, Peng Zhao, Boyuan Xu, Di Qiu, Debang Li, Zhengcong Fei, Yang Li, Yahui Zhou

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Video
Task
Video generation, Image-to-video, Text-to-video
Base model
Qwen2.5-VL-7B

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
14B

14B

Training data
tokens

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A800 SXM
Chips used
64
Power draw
50.2 kW

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident
Citations
142

Sources

Where this record came from and when it was last checked.

Reference
SkyReels-V2: Infinite-length Film Generative Model
Last updated
25 May 2026

What the numbers mean

About this model

SkyReels-V2 was published by Kunlun Inc., in the country recorded as China, during April 2025. It comes out of an organisation categorised as industry.

It works in the domain of Video, and is recorded as performing the task of video generation, Image-to-video, Text-to-video.

Rather than being trained from scratch, it is derived from Qwen2.5-VL-7B. That is why it shares the base model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

SkyReels-V2 — common questions

01

SkyReels-V2— what is it used for?

It works in the domain of Video, and is recorded as handling the task of video generation, Image-to-video, Text-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

SkyReels-V2— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

03

SkyReels-V2— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

04

SkyReels-V2— how many parameters does it have?

It has a parameter count of 14B. 14B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

05

SkyReels-V2— who created it?

It was published by Kunlun Inc., based in China, an organisation categorised as industry.

06

SkyReels-V2— when was it released?

It was published in April 2025.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.