SkyReels-V3-A2V-19B
Built by Skywork, SkyReels-V3-A2V-19B is a 19 billion parameter image-generation model. SkyReels-V3-A2V-19B is an open-weights image model with roughly 19 billion parameters.
by Skywork · 19B parameters
Best for
Ways to use SkyReels-V3-A2V-19B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Skywork API key. osFoundry discovers SkyReels-V3-A2V-19B 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-V3-A2V-19B 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-V3-A2V-19B
SkyReels-V3-A2V-19B runs on a single 16GB consumer GPU (~12 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~46 GB).
SkyReels-V3-A2V-19B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SkyReels-V3-A2V-19B
Is SkyReels-V3-A2V-19B free to use?
SkyReels-V3-A2V-19B 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-V3-A2V-19B 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-V3-A2V-19B need?
Approximately 12 GB at Q4 quantisation, or 46 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SkyReels-V3-A2V-19B locally?
Yes. SkyReels-V3-A2V-19B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SkyReels-V3-A2V-19B best at?
SkyReels-V3-A2V-19B is well-suited to image to video.
How do I use SkyReels-V3-A2V-19B in osFoundry?
Paste your Skywork API key in the key dialog (or deploy the open weights for self-hostable models), assign SkyReels-V3-A2V-19B 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 January 19, 2026. Source: https://huggingface.co/Skywork/SkyReels-V3-A2V-19B