shapes

desert-ant-labs/shapes

shapes is a image classification model from desert-ant-labs. Use it when you need a label for an image. It is set up for litert. The card lists the license as other.

Downloads · 30 days

8.7K

68% of all-time downloads

All-time downloads

12.8K

Public

Repo size

1.7 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.tflite1.3 MB · 75%

At a glance

Task: Image Classification
Library: litert
License: other
Access: Public
Created: Jun 23, 2026
Updated: Oct 3, 2026
SHA: ac74e0c0

Spaces

Model card

From the Hugging Face model README

Shapes

Rough sketch. Perfect shape.

On-device single-stroke shape recognition.

SDKs, install and examples: https://github.com/Desert-Ant-Labs/desert-ant-core/blob/main/docs/models/shapes.md
Website: https://desertant.com/models/shapes/

Turn a rough circle drawing into a clean shape, with fitted vector geometry ready to snap to. Built for PencilKit-style "smart shapes": draw, pause, and the rough stroke becomes a crisp shape. The model is tiny (200KB Core ML, 1.3MB LiteRT) and runs in a few milliseconds on device.

✏️ ➜ ▭ · ✏️ ➜ △ · ✏️ ➜ ◯ · ✏️ ➜ ★

Try it

Live demo: desert-ant-labs/shapes-demo: draw one stroke, get a fitted shape, fully in your browser.


Platforms	iOS, macOS, tvOS, visionOS, Android, Linux, Windows, Browser, Node
Weights	v0.3.0

Install

Swift (requirements)

.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core.git", from: "3.6.0")

Then add the Shapes product to your target.

Kotlin (requirements)

implementation("ai.desertant:shapes:3.6.0")

JavaScript (requirements)

npm i @desert-ant-labs/shapes @litertjs/core   # browser
npm i @desert-ant-labs/shapes                  # Node, prebuilt native core

Files

File	Format	Size	Contents
`shapes.tflite`	LiteRT / TFLite (fp32)	1.3MB	Fixed `[1,256,3]` features + `[1,256]` mask window; runs on Android, Linux, Node, and the web (bundled by default in the Kotlin SDK; downloaded on demand by the JavaScript SDK)
`shapes.mlmodelc`	Compiled Core ML	200KB	4-bit-palettized classifier, ready to load on Apple platforms (used by the Swift SDK)
`shapes_meta.json`	JSON	tiny	classes, preprocessing constants, model dims, and snap gates
`shapes.safetensors`	safetensors	200KB	Packed weights for SDK versions before the LiteRT migration (tag `v0.1.0`)

Inputs and outputs

Input: an ordered list of stroke points in canvas coordinates. Single stroke.
Output: a shape class plus fitted geometry, or nothing if the stroke is rejected.

Classes

line, rectangle, triangle, ellipse, star, plus none (the reject class: scribbles, partial shapes, and other non-shape strokes). Squares and circles are covered by rectangle and ellipse (snapped when near-regular).

Limitations

Single stroke only; multi-stroke shapes aren't recognized.
Tuned for deliberate shapes; very rough or ambiguous strokes are rejected by design.

License

Desert Ant Labs Source-Available License. Free for most apps, and a commercial license is required at scale. Full terms are at the link. Licensing: [email protected].

See THIRD_PARTY_NOTICES.md.

Citation

@software{shapes_2026,
  title  = {Shapes: On-device single-stroke shape recognition},
  author = {Desert Ant Labs},
  year   = {2026},
  url    = {https://huggingface.co/desert-ant-labs/shapes},
}

Task: Image Classification
Library: litert
License: other
Created: Jun 23, 2026
Updated: Oct 3, 2026