Cosmos-Predict2-2B-Text2Image
Cosmos-Predict2-2B-Text2Image is a 2 billion parameter image-generation model from nvidia, released April 22, 2025. Cosmos-Predict2-2B-Text2Image is an open-weights image model with roughly 2 billion parameters.
by nvidia · 2B parameters
Best for
Ways to use Cosmos-Predict2-2B-Text2Image in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your nvidia API key. osFoundry discovers Cosmos-Predict2-2B-Text2Image 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
Cosmos-Predict2-2B-Text2Image 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 Cosmos-Predict2-2B-Text2Image
Cosmos-Predict2-2B-Text2Image runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
Cosmos-Predict2-2B-Text2Image vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Cosmos-Predict2-2B-Text2Image
Is Cosmos-Predict2-2B-Text2Image free to use?
Cosmos-Predict2-2B-Text2Image 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 Cosmos-Predict2-2B-Text2Image 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 Cosmos-Predict2-2B-Text2Image need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Cosmos-Predict2-2B-Text2Image locally?
Yes. Cosmos-Predict2-2B-Text2Image is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Cosmos-Predict2-2B-Text2Image best at?
Cosmos-Predict2-2B-Text2Image is well-suited to text to image.
How do I use Cosmos-Predict2-2B-Text2Image in osFoundry?
Paste your nvidia API key in the key dialog (or deploy the open weights for self-hostable models), assign Cosmos-Predict2-2B-Text2Image to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by nvidia on April 22, 2025. Source: https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image