Instructions to use diffusionstudio/sam2.1-large-video-onnx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use diffusionstudio/sam2.1-large-video-onnx-fp16 with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("diffusionstudio/sam2.1-large-video-onnx-fp16") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained("diffusionstudio/sam2.1-large-video-onnx-fp16") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>) # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
Download onnx/memory_encoder.onnx from diffusionstudio/sam2.1-large-video-onnx-fp16: direct link, hf CLI and curl.
- Browser
- Download file 2.81 MB
-
https://huggingface.co/diffusionstudio/sam2.1-large-video-onnx-fp16/resolve/main/onnx/memory_encoder.onnx
- Command line
-
hf download hf://diffusionstudio/sam2.1-large-video-onnx-fp16/onnx/memory_encoder.onnx
-
curl -L -o memory_encoder.onnx https://huggingface.co/diffusionstudio/sam2.1-large-video-onnx-fp16/resolve/main/onnx/memory_encoder.onnx
2.81 MB
- Xet hash:
- c612b69e149fa6333badad2735a959e0334a80fd58e6edc56e07f0a4ac64a9c8
- Size of remote file:
- 2.81 MB
- SHA256:
- c809462a85e2354437e705a70bbb5a74f9194e28db7443dd69f68b8ae4f4047d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.