Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/breezewhite/interesting-colabs

Personal colab collections which I feel interesting.
https://github.com/breezewhite/interesting-colabs

fun google-colab

Last synced: 3 days ago
JSON representation

Personal colab collections which I feel interesting.

Awesome Lists containing this project

README

        

# Interesting Colabs

Personal colab collections which I feel interesting and wrap the original project into
easy-to-use colab scripts.

## Image

| Name | Description | Source |
|----------------------|-------------------------------------------------------|--------|
| Informative Drawings | Transform pictures into line-drawing style images. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/InformativeDrawings.ipynb) / [Github](https://github.com/carolineec/informative-drawings) |
| ArtLine | Similar to above, but different style. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/ArtLine.ipynb) / [Github](https://github.com/vijishmadhavan/ArtLine) |
| Upscale Image | Increase the resolution of an image. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/UpscaleImage.ipynb) / [Github](https://github.com/idealo/image-super-resolution) |
| AnimeGANv2 | Transform pictures into different anime style images. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/AnimeGanV2.ipynb) / [Github](https://github.com/TachibanaYoshino/AnimeGANv2) |
| ArcaneGAN | Transform pictures into Arcane-like images. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/ArcaneGAN.ipynb) / [Github](https://github.com/Sxela/ArcaneGAN) |
| JoJoGAN | Transform photos into various styles. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/JoJoGAN.ipynb) / [Github](https://github.com/mchong6/JoJoGAN) |
| AnycostGAN | Adjust one's face apperance with various properties. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/AnycostGAN.ipynb) / [Github](https://github.com/mit-han-lab/anycost-gan) |
| NeuralStyleTransfer | Transfer the style of the original image to target image style. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/NeuralStyleTransfer.ipynb) / [Github](https://github.com/titu1994/Neural-Style-Transfer) |
| Restormer | Image restoration. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/Restormer.ipynb) / [Github](https://github.com/swz30/Restormer) |
| DualStyleGAN | Turn image into Pixal, cartoon, and more other styles | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/DualStyleGAN.ipynb) / [Github](https://github.com/williamyang1991/DualStyleGAN) |
| Neural Painting | Paint the image in different painting styles. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/NeuralPainting.ipynb) / [Github](https://github.com/jiupinjia/stylized-neural-painting) |
| CLIPasso | Converting an image to a sketch composed with the given number of lines. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/CLIPasso.ipynb) / [Github](https://github.com/yael-vinker/CLIPasso) |

## Image Segmentation

| Name | Description | Source |
|----------------------|---------------------------------------------------|--------|
| segpeo | Segment people in the image and output the mask. | [Colab](https://colab.research.google.com/github/BreezeWhite/segpeo/blob/master/colab.ipynb) / [Github](https://github.com/BreezeWhite/segpeo) |

## Image-to-3D

| Name | Description | Source |
|----------------------|------------------------------------------------------------------|--------|
| PIFu | Reconstruct 3D human mesh from a single image | [Colab](https://colab.research.google.com/github/BreezeWhite/PIFu/blob/master/colab.ipynb) / [Github](https://github.com/BreezeWhite/PIFu) |
| PIFuHD | Improved version of PIFu. 3D human reconstruction from an image. | [Colab](https://colab.research.google.com/github/BreezeWhite/pifuhd/blob/master/colab.ipynb) / [Github](https://github.com/BreezeWhite/pifuhd) |

## Music

| Name | Description | Source |
|----------------------|-------------------------------------------------------|--------|
| Danna-Sep | Separate the given mixed audio into four sub-tracks. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/DannaSep.ipynb) / [Github](https://github.com/yoyololicon/danna-sep) |
| Demucs | Separate the given mixed audio into four sub-tracks. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/Demucs.ipynb) / [Github](https://github.com/facebookresearch/demucs) |
| Homr | Transform music sheet image into MusicXML file. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/Homr.ipynb) / [Github](https://github.com/liebharc/homr) |

## Text-to-Image

| Name | Description | Source |
|----------------------|-------------------------------------------------------------------------|--------|
| Diffusion 12M | Given any text prompt, the model generates the coressponding image. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/TextToImageDiffusion12M.ipynb) / [Github](https://github.com/crowsonkb/v-diffusion-pytorch) |
| Stable Diffusion | Text to image model provided by KerasCV. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/StableDiffusion.ipynb) / [Source](https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/) |
| Flex Diffusers | Extremely easy to use and highly adjustable text-to-image colab script. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/flex_diffusers.ipynb) / [Source](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb) |

## Text-to-Speech

| Name | Description | Source |
|----------------------|------------------------------------------------------|--------|
| CoquiTTS | Transform the input sentence into speech. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/CoquiTTS.ipynb) / [Github](https://github.com/coqui-ai/TTS/) |

## Video

| Name | Description | Source |
|----------------------|------------------------------------------------------------------|--------|
| Make It Talk | Make the image speak with the given text. | [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/MakeItTalk.ipynb) / [Github](https://github.com/yzhou359/MakeItTalk) |
| LifespanSynthesis | Synthesis one's face with different ages and render into a video.| [Colab](https://colab.research.google.com/github/BreezeWhite/interesting-colabs/blob/main/scripts/LifespanSynthesis.ipynb) / [Github](https://github.com/royorel/Lifespan_Age_Transformation_Synthesis) |