Model · Video

SkyReels V2

A downloadable video model from Skywork that makes clips from a description or a photo and can keep extending a clip to make much longer videos. The small version needs about 15 GB of graphics memory; the large ones need 40-50 GB or more.

Go to SkyReels V2’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Weights downloadable under the Skywork Community License, which has use restrictions; full licence PDF not read.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Licence: Skywork Community License (Community licence with conditions (e.g. revenue cap))
LICENSE.txt summarises the licence and links a PDF we didn't read. Bans unlawful or security-threatening use; asks for security reviews before running it as an internet service.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: Yes, with conditions
'The Skywork model supports commercial use', no application needed, but you must follow the full community licence (not read). No revenue cap or attribution rule seen in the summary.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: Free to download and run yourself
Plans below.
How you use it: On your own computer, Through another service
Weights on Hugging Face; Diffusers support marked done on GitHub. Optional prompt enhancer needs 64 GB+. Maker's hosted app at skyreels.ai.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
Our judgement: Python setup and a large GPU.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Skywork AI
No legal entity or country stated; licence contact address is at kunlun-inc.com.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Still downloadable, but the repo announced SkyReels-V3 weights on 29 Jan 2026 (not in our catalogue yet).
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A video, from a description (main use)
A video, by bringing a photo to life
A video, a longer version of a clip

text to videoimage to videovideo to video

Text-to-video, image-to-video and 'infinite-length' video by Diffusion Forcing (extension). Camera Director models listed as coming soon.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, Fotor, Genmo, getimg.ai, Google Flow

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.