OmniAvatar-14B
OmniAvatar-14B is a 14 billion parameter video-generation model from OmniAvatar, released June 17, 2025. OmniAvatar-14B is an open-weights video model with roughly 14 billion parameters.
by OmniAvatar · 14B parameters
Best for
Ways to use OmniAvatar-14B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OmniAvatar API key. osFoundry discovers OmniAvatar-14B 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
OmniAvatar-14B 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 OmniAvatar-14B
OmniAvatar-14B 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).
OmniAvatar-14B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about OmniAvatar-14B
Is OmniAvatar-14B free to use?
OmniAvatar-14B 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 OmniAvatar-14B 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 OmniAvatar-14B need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run OmniAvatar-14B locally?
Yes. OmniAvatar-14B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is OmniAvatar-14B best at?
OmniAvatar-14B is well-suited to text-to-video synthesis.
How do I use OmniAvatar-14B in osFoundry?
Paste your OmniAvatar API key in the key dialog (or deploy the open weights for self-hostable models), assign OmniAvatar-14B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by OmniAvatar on June 17, 2025. Source: https://huggingface.co/OmniAvatar/OmniAvatar-14B