VectorAscent
DALLECLIP
VectorAscent | DALLECLIP | |
---|---|---|
3 | 1 | |
113 | 2 | |
- | - | |
0.0 | 0.0 | |
almost 3 years ago | about 3 years ago | |
Python | Python | |
- | - |
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.
VectorAscent
-
test
(Added Mar. 9, 2021) VectorAscent by ajayjain. Uses diffvg to generate images.
-
Idea for developers: Use CLIP to steer a differentiable vector graphics generator
For future reference the actual code is here: https://github.com/ajayjain/VectorAscent
DALLECLIP
-
test
(Added Feb. 28, 2021) DALLECLIP by vipermu. Uses DALL-E's discrete VAE (variational autoencoder) component to generate images. Twitter reference.
What are some alternatives?
Colab-deep-daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network)
stylegan2-clip-approach - Navigating StyleGAN2 w latent space using CLIP
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
clipping-CLIP-to-GAN
random-colabs
StyleCLIP - Using CLIP and StyleGAN to generate faces from prompts.
TediGAN - [CVPR 2021] Pytorch implementation for TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
Story2Hallucination
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.
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
clip-glass - Repository for "Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search"