| # Cosmos Guardrail | |
| This page outlines a set of tools to ensure content safety in Cosmos. For implementation details, please consult the [Cosmos paper](https://research.nvidia.com/publication/2025-01_cosmos-world-foundation-model-platform-physical-ai). | |
| ## Overview | |
| Our guardrail system consists of two stages: pre-Guard and post-Guard. | |
| Cosmos pre-Guard models are applied to text input, including input prompts and upsampled prompts. | |
| * Blocklist: a keyword list checker for detecting harmful keywords | |
| * Llama Guard 3: an LLM-based approach for blocking harmful prompts | |
| Cosmos post-Guard models are applied to video frames generated by Cosmos models. | |
| * Video Content Safety Filter: a classifier trained to distinguish between safe and unsafe video frames | |
| * Face Blur Filter: a face detection and blurring module | |