The original algorithm from the paper Generative Art Using Neural Visual Grammars and Dual Encoders running on 1 GPU allows optimization of any image using a genetic algorithm. This is much more general but much slower than using Arnheim 2 which uses gradients.
iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based interface for interactively creating and editing imagery across categories such as landscapes, architecture, and fashion using pre-trained models. The system enables precise control over visual output through latent space exploration, interpolation, and projection. Users can guide the generative process using an interactive editor featuring sketching, coloring, and warping brushes to refine specific regions or shapes in real-time. The project supports both automated scripted gene
From RiversHaveWings aka @crowsonkb
[comment]: <> ()
The main features of gwang-kim/diffusionclip are: Image Generation.
Open-source alternatives to gwang-kim/diffusionclip include: afiaka87/clip-guided-diffusion — From RiversHaveWings aka @crowsonkb. deepmind/arnheim — The original algorithm from the paper Generative Art Using Neural Visual Grammars and Dual Encoders running on 1 GPU… hfailab/clip-gen — [简体中文][[English]](README_en.md). junyanz/igan — iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based… justinpinkney/clip2latent — ``bash git clone https://github.com/justinpinkney/clip2latent.git cd clip2latent python -m venv .venv --prompt… kundan2510/pixelcnn — Theano reimplementation of pixelCNN architecture.
