Cosmos3-Edge β Hexagon NPU (Image)
Prebuilt Qualcomm Hexagon NPU artifacts for the generation half of nvidia/Cosmos3-Edge β a diffusion model that runs on-device. It creates: given a text prompt, it synthesizes an image.
Capabilities
- Text-to-image β a diffusion-based generator that produces an image from a free-text prompt. Text in β image out.
This is a distinct network from the understanding model β a diffusion generator (with its own image decoder), not a language/vision-language model. It shares only the text-embedding table used to condition on the prompt.
Family β Cosmos3-Edge is shipped as two arch-pinned edge bundles by task:
- Cosmos3-Edge β Understanding β understanding (chat + vision), text output
- this repo β generation, image output
Artifacts are arch-pinned; this repo currently contains the v81/ directory.
For model architecture, intended use, limitations, and license terms, see the upstream model card: nvidia/Cosmos3-Edge. Distributed under the NVIDIA Open Model License inherited from the base model.
Model tree for runanywhere/cosmos3_edge_image_HNPU
Base model
nvidia/Cosmos3-Edge