stylized-neural-painting
notebooks
| stylized-neural-painting | notebooks | |
|---|---|---|
| 6 | 1 | |
| 1,536 | 41 | |
| - | - | |
| 0.0 | 5.2 | |
| over 2 years ago | 6 months ago | |
| Python | Jupyter Notebook | |
| Creative Commons Zero v1.0 Universal | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
stylized-neural-painting
-
I want to create an image to image transformer but I have no idea how to get started.
I want to create a Python program that takes in an image, paints over it, then spits out the resulting image. What I want to do is almost exactly like this project, but I want to do it from scratch, and make it more attuned to people's faces, as well as add more than just oil painting, pixel art, and marker strokes.
-
test
(Added Mar. 9, 2021) PaintCLIP.ipynb - Colaboratory by advadnoun. Uses Stylized Neural Painter to generate images. As of time of writing, this gave me an error message.
- I want to create a Stylized Neural Painting software
-
Combine neural painting with deepbrush for 100% realistic computer-made painting?
I think stroke-based painting methods like these are neat: https://github.com/jiupinjia/stylized-neural-painting https://github.com/fogleman/primitive
- Stylized Neural Painting
-
Idea for developers: Use CLIP to steer a differentiable vector graphics generator
Not exactly what you suggested, but pretty fun! Here's PaintCLIP using https://github.com/jiupinjia/stylized-neural-painting
notebooks
-
test
(Added Feb. 5, 2021) CLIP + TADNE (pytorch) v2 - Colaboratory_v2.ipynb) by nagolinc. Uses TADNE ("This Anime Does Not Exist") to generate images. Instructions and examples. GitHub. Notebook copy_v2.ipynb) by levindabhi
What are some alternatives?
Primitive Pictures - Reproducing images with geometric primitives.
aphantasia - CLIP + FFT/DWT/RGB = text to image/video
Story2Hallucination
VectorAscent - Generate vector graphics from a textual caption
deep-daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
AuViMi - AuViMi stands for audio-visual mirror. The idea is to have CLIP generate its interpretation of what your webcam sees, combined with the words thare are spoken.
Styleformer - A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.
Colab-deep-daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network)
big-sleep - A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
stylegan2-clip-approach - Navigating StyleGAN2 w latent space using CLIP
pytorch-AdaIN - Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]
clip_biggan