Model weights used by Image Cutout — Cut Out Anything From a Photo Online, Free (https://image-cutout.skillsafe.ai/)

This app runs 2 models on your device. About 32.9 MB of weights are downloaded from https://models.skillsafe.ai/ on first use and cached by your browser; inference happens locally and nothing you enter is uploaded to load them.

- SlimSAM-77 uniform segment anything (int8) (slimsam-77-uniform-int8@5850ab45, int8 dynamic-quantized) — 13.1 MB — Apache-2.0
  SlimSAM: 0.1% Data Makes Segment Anything Slim (Chen et al., NeurIPS 2024), a structural pruning of Meta's Segment Anything ViT-B. ONNX int8 dynamic-quantized export of the 77%-pruned uniform model published by Xenova on Hugging Face. Licensed under the Apache License 2.0.
  Notice: https://huggingface.co/Xenova/slimsam-77-uniform
  Source: https://huggingface.co/Xenova/slimsam-77-uniform/tree/5850ab45f587c112167512ffef949107115e26a0
- SlimSAM-77 uniform segment anything (fp16) (slimsam-77-uniform-fp16@5850ab45, fp16) — 19.8 MB — Apache-2.0
  SlimSAM: 0.1% Data Makes Segment Anything Slim (Chen et al., NeurIPS 2024), a structural pruning of Meta's Segment Anything ViT-B. ONNX fp16 export of the 77%-pruned uniform model published by Xenova on Hugging Face. Licensed under the Apache License 2.0.
  Notice: https://huggingface.co/Xenova/slimsam-77-uniform
  Source: https://huggingface.co/Xenova/slimsam-77-uniform/tree/5850ab45f587c112167512ffef949107115e26a0

Catalogue: https://api.skillsafe.ai/v1/browser-models