SkyReels-V2-T2V-14B-540P
SkyReels-V2-T2V-14B-540P (Skywork, 2025) is a 14 billion parameter video-generation model. SkyReels-V2-T2V-14B-540P is an open-weights video model with roughly 14 billion parameters.
by Skywork · 14B parameters
Best for
Ways to use SkyReels-V2-T2V-14B-540P in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Skywork API key. osFoundry discovers SkyReels-V2-T2V-14B-540P automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
SkyReels-V2-T2V-14B-540P is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run SkyReels-V2-T2V-14B-540P
SkyReels-V2-T2V-14B-540P runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~34 GB).
SkyReels-V2-T2V-14B-540P vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SkyReels-V2-T2V-14B-540P
Is SkyReels-V2-T2V-14B-540P free to use?
SkyReels-V2-T2V-14B-540P is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use SkyReels-V2-T2V-14B-540P commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does SkyReels-V2-T2V-14B-540P need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SkyReels-V2-T2V-14B-540P locally?
Yes. SkyReels-V2-T2V-14B-540P is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SkyReels-V2-T2V-14B-540P best at?
SkyReels-V2-T2V-14B-540P is well-suited to text-to-video synthesis.
How do I use SkyReels-V2-T2V-14B-540P in osFoundry?
Paste your Skywork API key in the key dialog (or deploy the open weights for self-hostable models), assign SkyReels-V2-T2V-14B-540P to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Skywork on April 18, 2025. Source: https://huggingface.co/Skywork/SkyReels-V2-T2V-14B-540P