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 / Github |
ArtLine |
Similar to above, but different style. |
Colab / Github |
Upscale Image |
Increase the resolution of an image. |
Colab / Github |
AnimeGANv2 |
Transform pictures into different anime style images. |
Colab / Github |
ArcaneGAN |
Transform pictures into Arcane-like images. |
Colab / Github |
JoJoGAN |
Transform photos into various styles. |
Colab / Github |
AnycostGAN |
Adjust one's face apperance with various properties. |
Colab / Github |
NeuralStyleTransfer |
Transfer the style of the original image to target image style. |
Colab / Github |
Restormer |
Image restoration. |
Colab / Github |
DualStyleGAN |
Turn image into Pixal, cartoon, and more other styles |
Colab / Github |
Neural Painting |
Paint the image in different painting styles. |
Colab / Github |
CLIPasso |
Converting an image to a sketch composed with the given number of lines. |
Colab / Github |
Image Segmentation
Name |
Description |
Source |
segpeo |
Segment people in the image and output the mask. |
Colab / Github |
Image-to-3D
Name |
Description |
Source |
PIFu |
Reconstruct 3D human mesh from a single image |
Colab / Github |
PIFuHD |
Improved version of PIFu. 3D human reconstruction from an image. |
Colab / Github |
Music
Name |
Description |
Source |
Danna-Sep |
Separate the given mixed audio into four sub-tracks. |
Colab / Github |
Demucs |
Separate the given mixed audio into four sub-tracks. |
Colab / Github |
Text-to-Image
Name |
Description |
Source |
Diffusion 12M |
Given any text prompt, the model generates the coressponding image. |
Colab / Github |
Stable Diffusion |
Text to image model provided by KerasCV. |
Colab / Source |
Flex Diffusers |
Extremely easy to use and highly adjustable text-to-image colab script. |
Colab Source |
Text-to-Speech
Name |
Description |
Source |
CoquiTTS |
Transform the input sentence into speech. |
Colab / Github |
Video
Name |
Description |
Source |
Make It Talk |
Make the image speak with the given text. |
Colab / Github |
LifespanSynthesis |
Synthesis one's face with different ages and render into a video. |
Colab / Github |