<p align="center">
<picture>
<img alt="kiuikit_logo" src="docs/source/_static/logo.png" width="50%">
</picture>
</br>
<b>Kiuikit</b>
</br>
<code>pip install kiui</code>
•
<a href="https://kit.kiui.moe/">Documentation</a>
</p>
A toolkit for computer vision (especially 3D vision) tasks.
**Features**:
* Collection of *maintained, reusable and trustworthy* code snippets.
* Always using lazy import so the code is not slowed down by `import kiui`.
* Useful CLI tools, such as a GUI mesh renderer.
https://github.com/ashawkey/kiuikit/assets/25863658/d8cbcf0f-a6d8-4fa7-aee9-afbbf25ed167
> ["Seahourse3"](https://skfb.ly/6TwFv) by seanhepburn is licensed under [Creative Commons Attribution](http://creativecommons.org/licenses/by/4.0/).
### Install
```bash
# 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
```
### Basic Usage
```python
import kiui
### quick inspection of array-like object
x = torch.tensor(...)
y = np.array(...)
kiui.lo(x)
kiui.lo(x, y) # support multiple objects
kiui.lo(kiui) # or any other object (just print with name)
### io utils
# read image as-is in RGB order
img = kiui.read_image('image.png', mode='float') # mode: float (default), pil, uint8, tensor
# write image
kiui.write_image('image.png', img)
### visualization tools
img_tensor = torch.rand(3, 256, 256)
# tensor of [3, H, W], [1, H, W], [H, W] / array of [H, W ,3], [H, W, 1], [H, W] in [0, 1]
kiui.vis.plot_image(img)
kiui.vis.plot_image(img_tensor)
### mesh utils
from kiui.mesh import Mesh
mesh = Mesh.load('model.obj')
kiui.lo(mesh.v, mesh.f) # CUDA torch.Tensor suitable for nvdiffrast
mesh.write('new.obj')
mesh.write('new.glb') # support exporting to GLB/GLTF too (texture embedded).
# perceptual loss (from https://github.com/richzhang/PerceptualSimilarity)
from kiui.lpips import LPIPS
lpips = LPIPS(net='vgg').cuda()
loss = lpips(input, target) # [B, 3, H, W] image in [-1, 1]
```
CLI tools:
```bash
# sr (Real-ESRGAN from https://github.com/ai-forever/Real-ESRGAN/tree/main)
python -m kiui.sr --help
python -m kiui.sr image.jpg --scale 2 # save to image_2x.jpg
kisr image.jpg --scale 2 # short cut cmd
# mesh format conversion (only for a single textured mesh in obj/glb)
python -m kiui.cli.convert input.obj output.glb
kico input.obj output.glb # short cut cmd
kico mesh_folder video_folder --in_fmt .glb --out_fmt .mp4 # render all glb meshes into rotating videos
# aesthetic predictor v2 (https://github.com/christophschuhmann/improved-aesthetic-predictor)
python -m kiui.cli.aes --help
# compare content of two directories
python -m kiui.cli.dircmp <dir1> <dir2>
# lock requirements.txt package versions based on current environment
python -m kiui.cli.lock_version <requirements.txt>
```
GUI tools:
```bash
# open a GUI to render a mesh (extra dep: nvdiffrast)
python -m kiui.render --help
python -m kiui.render mesh.obj
python -m kiui.render mesh.glb --pbr # render with PBR (metallic + roughness)
python -m kiui.render mesh.obj --save_video out.mp4 --wogui # save 360 degree rotating video
kire --help # short cut cmd
# open a GUI to render and edit pose (openpose convention, controlnet compatible)
python -m kiui.poser --help
python -m kiui.poser --load 3head # load preset 3 headed skeleton
```
Raw data
{
"_id": null,
"home_page": "https://github.com/ashawkey/kiuikit",
"name": "kiui",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "utility",
"author": "kiui",
"author_email": "ashawkey1999@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/d2/7f/aa68cf1db675d4c4a57bd2de60d94293bcb6cedc2e66d0e119dd77bf4677/kiui-0.2.8.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <picture>\n <img alt=\"kiuikit_logo\" src=\"docs/source/_static/logo.png\" width=\"50%\">\n </picture>\n </br>\n <b>Kiuikit</b>\n </br>\n <code>pip install kiui</code>\n • \n <a href=\"https://kit.kiui.moe/\">Documentation</a>\n</p>\n\nA toolkit for computer vision (especially 3D vision) tasks.\n\n**Features**:\n* Collection of *maintained, reusable and trustworthy* code snippets.\n* Always using lazy import so the code is not slowed down by `import kiui`.\n* Useful CLI tools, such as a GUI mesh renderer.\n\nhttps://github.com/ashawkey/kiuikit/assets/25863658/d8cbcf0f-a6d8-4fa7-aee9-afbbf25ed167\n\n> [\"Seahourse3\"](https://skfb.ly/6TwFv) by seanhepburn is licensed under [Creative Commons Attribution](http://creativecommons.org/licenses/by/4.0/).\n\n### Install\n\n```bash\n# released\npip install kiui # install the minimal package\npip install kiui[full] # install optional dependencies\n\n# latest\npip install git+https://github.com/ashawkey/kiuikit.git # only the minimal package\n```\n\n### Basic Usage\n\n```python\nimport kiui\n\n### quick inspection of array-like object\nx = torch.tensor(...)\ny = np.array(...)\n\nkiui.lo(x)\nkiui.lo(x, y) # support multiple objects\nkiui.lo(kiui) # or any other object (just print with name)\n\n### io utils\n# read image as-is in RGB order\nimg = kiui.read_image('image.png', mode='float') # mode: float (default), pil, uint8, tensor\n# write image\nkiui.write_image('image.png', img)\n\n### visualization tools\nimg_tensor = torch.rand(3, 256, 256) \n# tensor of [3, H, W], [1, H, W], [H, W] / array of [H, W ,3], [H, W, 1], [H, W] in [0, 1]\nkiui.vis.plot_image(img)\nkiui.vis.plot_image(img_tensor)\n\n### mesh utils\nfrom kiui.mesh import Mesh\nmesh = Mesh.load('model.obj')\nkiui.lo(mesh.v, mesh.f) # CUDA torch.Tensor suitable for nvdiffrast\nmesh.write('new.obj')\nmesh.write('new.glb') # support exporting to GLB/GLTF too (texture embedded).\n\n# perceptual loss (from https://github.com/richzhang/PerceptualSimilarity)\nfrom kiui.lpips import LPIPS\nlpips = LPIPS(net='vgg').cuda()\nloss = lpips(input, target) # [B, 3, H, W] image in [-1, 1]\n```\n\nCLI tools:\n```bash\n# sr (Real-ESRGAN from https://github.com/ai-forever/Real-ESRGAN/tree/main)\npython -m kiui.sr --help\npython -m kiui.sr image.jpg --scale 2 # save to image_2x.jpg\nkisr image.jpg --scale 2 # short cut cmd\n\n# mesh format conversion (only for a single textured mesh in obj/glb)\npython -m kiui.cli.convert input.obj output.glb\nkico input.obj output.glb # short cut cmd\nkico mesh_folder video_folder --in_fmt .glb --out_fmt .mp4 # render all glb meshes into rotating videos\n\n# aesthetic predictor v2 (https://github.com/christophschuhmann/improved-aesthetic-predictor)\npython -m kiui.cli.aes --help\n\n# compare content of two directories\npython -m kiui.cli.dircmp <dir1> <dir2>\n\n# lock requirements.txt package versions based on current environment\npython -m kiui.cli.lock_version <requirements.txt>\n```\n\nGUI tools:\n```bash\n# open a GUI to render a mesh (extra dep: nvdiffrast)\npython -m kiui.render --help\npython -m kiui.render mesh.obj\npython -m kiui.render mesh.glb --pbr # render with PBR (metallic + roughness)\npython -m kiui.render mesh.obj --save_video out.mp4 --wogui # save 360 degree rotating video\nkire --help # short cut cmd\n\n# open a GUI to render and edit pose (openpose convention, controlnet compatible)\npython -m kiui.poser --help\npython -m kiui.poser --load 3head # load preset 3 headed skeleton\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "A toolkit for 3D vision",
"version": "0.2.8",
"project_urls": {
"Homepage": "https://github.com/ashawkey/kiuikit"
},
"split_keywords": [
"utility"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c8315066807c7c0fe4f538b9ef0b4f5fa7eb2ccc238e85fdc620ee8e449a0fe5",
"md5": "f904eb77c5f425cd4b073b9d588ebe73",
"sha256": "59f9c28dcd1be9e8c2d04ebe0c78bb1af807af6eaade9b5e4c659c6e088f9ac8"
},
"downloads": -1,
"filename": "kiui-0.2.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f904eb77c5f425cd4b073b9d588ebe73",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 3082482,
"upload_time": "2024-04-25T08:30:18",
"upload_time_iso_8601": "2024-04-25T08:30:18.508619Z",
"url": "https://files.pythonhosted.org/packages/c8/31/5066807c7c0fe4f538b9ef0b4f5fa7eb2ccc238e85fdc620ee8e449a0fe5/kiui-0.2.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d27faa68cf1db675d4c4a57bd2de60d94293bcb6cedc2e66d0e119dd77bf4677",
"md5": "c308ab8d895ffc8abb3b2562a31a6222",
"sha256": "5ba4fda321a192f897b4a6e00955b2ad595b19bea56cead65ed7e4e158b911a1"
},
"downloads": -1,
"filename": "kiui-0.2.8.tar.gz",
"has_sig": false,
"md5_digest": "c308ab8d895ffc8abb3b2562a31a6222",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 3056819,
"upload_time": "2024-04-25T08:30:20",
"upload_time_iso_8601": "2024-04-25T08:30:20.484104Z",
"url": "https://files.pythonhosted.org/packages/d2/7f/aa68cf1db675d4c4a57bd2de60d94293bcb6cedc2e66d0e119dd77bf4677/kiui-0.2.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-25 08:30:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ashawkey",
"github_project": "kiuikit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "kiui"
}