SkyReels-V2
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
- Training data
- tokens
14B
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 China, in April 2025. It comes out of industry.
It works in Video, and is recorded as doing video generation, Image-to-video, Text-to-video.
It is derived from Qwen2.5-VL-7B rather than trained from scratch, which is the usual way a specialised model is produced.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
SkyReels-V2 — common questions
What is SkyReels-V2 used for?
SkyReels-V2 works in Video, and is recorded as handling video generation, Image-to-video, Text-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run SkyReels-V2?
None. SkyReels-V2 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.
Is SkyReels-V2 open source?
The licensing for SkyReels-V2 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does SkyReels-V2 have?
SkyReels-V2 has 14B parameters. 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.
Who created SkyReels-V2?
SkyReels-V2 was published by Kunlun Inc., based in China, categorised as industry.
When was SkyReels-V2 released?
SkyReels-V2 was published in April 2025.
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.