Instructions to use DiffusionWave/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DiffusionWave/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="DiffusionWave/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("DiffusionWave/sam3") model = AutoModel.from_pretrained("DiffusionWave/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download sam3.pt from DiffusionWave/sam3: direct link, hf CLI and curl.
- Browser
- Download file 3.45 GB
-
https://huggingface.co/DiffusionWave/sam3/resolve/main/sam3.pt
- Command line
-
hf download hf://DiffusionWave/sam3/sam3.pt
-
curl -L -o sam3.pt https://huggingface.co/DiffusionWave/sam3/resolve/main/sam3.pt
3.45 GB
- Xet hash:
- ba62acd04c1fe8f3d6096b1552e6ca28a2f7c7380f931040f5719a2bcdf844ad
- Size of remote file:
- 3.45 GB
- SHA256:
- 9999e2341ceef5e136daa386eecb55cb414446a00ac2b55eb2dfd2f7c3cf8c9e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.