Cosmos-Transfer2.5 diffusion models are a collection of diffusion based world foundation models that generate dynamic, high quality images and videos from text, image, or control video inputs.
Cosmos Transfer-2.5 2B Container Overview
Description:
This container houses Cosmos-Transfer2.5. Cosmos-Transfer2.5 diffusion models are a collection of diffusion based world foundation models that generate dynamic, high quality images and videos from text, image, or control video inputs. It can serve as the building block for various applications or research that are related to world generation.
Cosmos-Transfer2.5 is part of a family of highly performant pre-trained world foundation models purpose-built for generating physics-aware images, videos and world states aligned with the input control conditions.
The container components are ready for commercial use.
License/Terms of Use:
GOVERNING TERMS: Use of the software is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography:
Global
Release Date:
- Huggingface 10/06/2025 via https://huggingface.co/nvidia/Cosmos-Transfer2.5-2B
- Github 10/06/2025 via https://github.com/nvidia-cosmos/cosmos-transfer2.5
Cosmos Transfer-2.5 2B NIM:
This NIM houses the Cosmos Transfer-2.5 2B model:
| Model Name | Use Case | How to pull the Model |
|---|---|---|
| Cosmos Transfer 2.5 2B | It can serve as the building block for various applications or research that are related to world generation. | Automatic |
Deployment Details:
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Visit the NVIDIA NIM for Cosmos page for release documentation, deployment guides and more.
Container Version(s):
nvcr.io/nim/nvidia/cosmos-transfer2.5-2b:latest
nvcr.io/nim/nvidia/cosmos-transfer2.5-2b:1.1
Nim optimizations:
The NIM container includes numerous performance optimizations over the open-source version, most notably:
- NVIDIA TensorRT inference framework
- Model quantization (FP8)
- Latency and throughput optimized inference profiles
Security Common Vulnerabilities and Exposures (CVEs):
Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the Cosmos Transfer-2.5 2B NIM page for release documentation, deployment guides and more.
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.