# ShowUI-π checkpoint

A compact visual-action checkpoint that predicts continuous GUI drag trajectories from a screenshot and a natural-language instruction.

- Catalog URL: https://awesomecua.github.io/resources/url-f70aa7c95824a8729516/
- Original source: https://huggingface.co/showlab/ShowUI-pi
- Kind: model
- Review: curated
- Scope: core
- Environments: unspecified
- Topics: grounding, action-prediction
- Evidence checked: 2026-10-17T02:44:50Z
- ID: url:f70aa7c95824a8729516

## Limitations

A model.safetensors file and policy pre/postprocessor configuration are publicly ungated. The card describes a SmolVLA-based GUI drag-and-drop model despite its generic robotics pipeline tag. No weight-license declaration or specific operating-system coverage is provided.

- Record JSON: https://awesomecua.github.io/resources/url-f70aa7c95824a8729516/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://huggingface.co/showlab/ShowUI-pi/raw/main/README.md (retrieved 2026-10-17T02:44:50Z; SHA-256 64993ab5dc8205e25bda2576055b7e252104c67d4e6eeecb33a1a9742415f67e)
- https://huggingface.co/api/models/showlab/ShowUI-pi (retrieved 2026-10-17T02:44:50Z; SHA-256 ae12ece91946d79c5c6b578d6db07b5f095822be1ca3bc14bb3dc04a771bb010)