How to use moonbox-dev/sam2.1-hiera-large-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download moonbox-dev/sam2.1-hiera-large-MLX --local-dir sam2.1-hiera-large-MLX
How to use moonbox-dev/sam2.1-hiera-large-MLX with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("moonbox-dev/sam2.1-hiera-large-MLX") 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("moonbox-dev/sam2.1-hiera-large-MLX") 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): ...
