Instructions to use nvidia/DAM-3B-Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Describe Anything
How to use nvidia/DAM-3B-Video with Describe Anything:
# pip install git+https://github.com/NVlabs/describe-anything from huggingface_hub import snapshot_download from dam import DescribeAnythingModel snapshot_download(nvidia/DAM-3B-Video, local_dir="checkpoints") dam = DescribeAnythingModel( model_path="checkpoints", conv_mode="v1", prompt_mode="focal_prompt", )
- Notebooks
- Google Colab
- Kaggle
Non free software license, this is proprietary model.
#2
by JLouisBiz - opened
Why don't you publish on the free software license? This is proprietary and not allowed for commercial use.
Thanks! The models are intended to be used for educational and research purposes. We cannot make models permissive for commercial use mainly because of the constraints from the training datasets we used, such as SAM (https://ai.meta.com/datasets/segment-anything-downloads/).
richardaecn changed discussion status to closed
Sad to see how rooted bad decisions influence the world. Good for research but not as good as how it would be with truly free software, look how much publicity and good image goes to Qwen, DeepSeek, AllenAI, Microsoft, IBM, ByteDance for their fully free software models