Spatial-MLLM-v1.1-Instruct-820K
Diankun's Spatial-MLLM-v1.1-Instruct-820K is a video-generation model. Spatial-MLLM-v1.1-Instruct-820K is an open-weights video model.
by Diankun
Best for
Ways to use Spatial-MLLM-v1.1-Instruct-820K in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Diankun API key. osFoundry discovers Spatial-MLLM-v1.1-Instruct-820K 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
Spatial-MLLM-v1.1-Instruct-820K 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.
Spatial-MLLM-v1.1-Instruct-820K vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Spatial-MLLM-v1.1-Instruct-820K | Diankun | — | — | Free (local) | Yes |
| Vista4D | Eyeline-Labs | — | — | Free (local) | Yes |
| VITA-1.5 | VITA-MLLM | — | — | Free (local) | Yes |
| LTX-Video-0.9.1 | Lightricks | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Spatial-MLLM-v1.1-Instruct-820K
Is Spatial-MLLM-v1.1-Instruct-820K free to use?
Spatial-MLLM-v1.1-Instruct-820K 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 Spatial-MLLM-v1.1-Instruct-820K commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run Spatial-MLLM-v1.1-Instruct-820K locally?
Yes. Spatial-MLLM-v1.1-Instruct-820K is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Spatial-MLLM-v1.1-Instruct-820K best at?
Spatial-MLLM-v1.1-Instruct-820K is well-suited to video text to text.
How do I use Spatial-MLLM-v1.1-Instruct-820K in osFoundry?
Paste your Diankun API key in the key dialog (or deploy the open weights for self-hostable models), assign Spatial-MLLM-v1.1-Instruct-820K to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Diankun on January 5, 2026. Source: https://huggingface.co/Diankun/Spatial-MLLM-v1.1-Instruct-820K