tmappdev/lang-segment-anything 🖼️📝 → 🖼️

▶️ 1.7M runs 📅 Nov 2024 ⚙️ Cog 0.13.2

image-segmentation language-guided-segmentation text-guided-segmentation

About

Segment Anything with prompts

Example Output

Output

Performance Metrics

2.24s Prediction Time

42.59s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/M2tUXKe06UEAExSwWbcYvMOoGVXGtEbvsD52HaSgC3vulSfR/a2ed4.jpg",
  "text_prompt": "text,watermark"
}

Input Parameters

image (required) Type: string: Path to the input image
text_prompt (required) Type: string: Text prompt for segmentation

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Predicting 1 masks
/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torchvision/transforms/functional.py:154: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)
img = torch.from_numpy(pic.transpose((2, 0, 1))).contiguous()
Predicted 1 masks

Version Details

Version ID: 891411c38a6ed2d44c004b7b9e44217df7a5b07848f29ddefd2e28bc7cbf93bc
Version Created: November 27, 2024

Run on Replicate →