kiui · PyPI

kiuikit_logo
Kiuikit
pip install kiui • Documentation

A niche toolkit for computer vision (especially 3D vision) tasks.

Install

# released
pip install kiui # install the minimal package
pip install kiui[full] # install optional dependencies

# latest
pip install git+https://github.com/ashawkey/kiuikit.git # only the minimal package

Highlights

CLI tools:

Command	Description
`kire`	GUI 3D mesh viewer with PBR rendering, auto-rotate, save video
`kisr`	Super-resolution (Real-ESRGAN)
`kivi`	Video/image info, resize, preview (capped-CRF), split
`kiss`	System information — OS, CPU, GPU, torch, CUDA, conda
`ks`	Slurm job management — queue, history, logs, cancel, usage
`kia`	AI coding agent — terminal-native with web UI, sub-agents, skills, and more

AI Agent (`kia`)

kia is a lightweight yet powerful coding agent.

pip install "kiui[kia]"
kia

What makes it different:

Native terminal + synchronized web UI, remote access from any browser.
Personal skill library kib: upload your own skills, download in any projects later.
Fully customizable personas.

See the agent documentation for full details.

Python library:

Module	Highlights
`kiui.lo()`	Rich-based inspection of arrays, tensors, and any object
`kiui.Mesh`	Torch-native 3D mesh — load `.obj/.glb/.ply/.fbx`, export, auto-UV, auto-normalize
`kiui.read_video` / `write_video`	Video I/O with numpy/torch support
`kiui.read_image` / `write_image`	Image I/O with float/HDR support
`kiui.op`	Vector math (`dot`, `length`, `safe_normalize`) working on both torch & numpy
`kiui.cam`	`OrbitCamera`, projection / unprojection utilities
`kiui.quaternion`	Quaternion math (norm, multiply, slerp, to/from matrices) for torch & numpy
`kiui.nn`	Standalone PyTorch NN blocks — MLP, DiT, UNet 2D/3D, VAE, attention, flow matching
`kiui.gridencoder`	Hash-grid encoding with CUDA backend
`kiui.lpips`	Clean LPIPS perceptual loss (SqueezeNet)
`kiui.timer`	CUDA-synchronized timer (context manager & decorator)
`kiui.equirect`	Equirectangular (360°) / cubemap utilities
`kiui.geocalib`	Single-image camera intrinsics estimation

See the documentation for full API details.

Metadata

Release files for kiui 0.3.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kiui 0.3.5
File	Size	Uploaded
kiui-0.3.5.tar.gz	3.5 MB	Jul 20, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for kiui 0.3.5
File	Interpreter	ABI	Platform	Reset
kiui-0.3.5-py3-none-any.whl 3.5 MB Jul 20, 2026	Python 3	none	any	Details

Total release size: 7.0 MB

Release files / kiui-0.3.5.tar.gz

Download URL	kiui-0.3.5.tar.gz
Size	3.5 MB
Tags	Source
SHA-256 checksum How to use checksums	`9c5867a22db12d559225ef13b902984db12a793fef391ae7bdca87910dc7cdfc`
BLAKE2b-256 checksum How to use checksums	`2b1333e4b9be95a447c8bcb0e8a07f37369066d5e8ce97f5af2c1795fd2af220`
Upload date	Jul 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/ashawkey/kiuikit
Publishing commit: github.com/ashawkey/kiuikit/tree/9c9d0331c302fd6aebd6100bae38a20f79d0a659

Workflow

Publishing configuration: github.com/ashawkey/kiuikit/blob/9c9d0331c302fd6aebd6100bae38a20f79d0a659/.github/workflows/pypi-publish.yml
Publishing logs: github.com/ashawkey/kiuikit/actions/runs/29742427395/attempts/1

Artifact

Subject: kiui-0.3.5.tar.gz
SHA-256 checksum: 9c5867a22db12d559225ef13b902984db12a793fef391ae7bdca87910dc7cdfc Verifying attestations

Release files / kiui-0.3.5-py3-none-any.whl

Download URL	kiui-0.3.5-py3-none-any.whl
Size	3.5 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`c629fd767a9559da72b5e8748226b227d4c6923fb568b8022eaf1e7686297f4c`
BLAKE2b-256 checksum How to use checksums	`110b06a0862730b49db18bce2e5dd09b0b36db8aa11964f9dc878c4d99f4b4b2`
Upload date	Jul 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/ashawkey/kiuikit
Publishing commit: github.com/ashawkey/kiuikit/tree/9c9d0331c302fd6aebd6100bae38a20f79d0a659

Workflow

Publishing configuration: github.com/ashawkey/kiuikit/blob/9c9d0331c302fd6aebd6100bae38a20f79d0a659/.github/workflows/pypi-publish.yml
Publishing logs: github.com/ashawkey/kiuikit/actions/runs/29742427395/attempts/1

Artifact

Subject: kiui-0.3.5-py3-none-any.whl
SHA-256 checksum: c629fd767a9559da72b5e8748226b227d4c6923fb568b8022eaf1e7686297f4c Verifying attestations