Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/francoyudica/genart

Image generation with genetic algorithms
https://github.com/francoyudica/genart

ai art compute-shader computer-graphics genetic-algorithm godot image-generation

Last synced: 3 days ago
JSON representation

Image generation with genetic algorithms

Host: GitHub
URL: https://github.com/francoyudica/genart
Owner: FrancoYudica
License: mit
Created: 2024-11-18T13:36:43.000Z (3 months ago)
Default Branch: main
Last Pushed: 2025-02-01T20:32:39.000Z (9 days ago)
Last Synced: 2025-02-01T21:28:37.375Z (9 days ago)
Topics: ai, art, compute-shader, computer-graphics, genetic-algorithm, godot, image-generation
Language: GDScript
Homepage:
Size: 102 MB
Stars: 48
Watchers: 1
Forks: 5
Open Issues: 7
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE

Awesome Lists containing this project

README

[![License](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://github.com/FrancoYudica/Genart/blob/main/LICENSE)

Genart is an application that transforms your target image into uniquely stylized artwork.
Smaller images are used as building blocks to reconstruct the target picture.

This tool is perfect for artists, designers, or anyone looking to experiment with creative and abstract image representations.

## Features

- Reconstruct any image using a chosen set of smaller images as building blocks.
- Save generated artwork in formats such as PNG, JPG, WEBP, and JSON for use in custom projects.
- Create animations with GenArt's integrated animator.
- Optimize results easily with predefined FAST, PERFORMANCE, and QUALITY modes.
- Utilize default image collections for effortless creation.
- Customize algorithms with an extensive range of settings.
- Prioritize specific areas of the target image using a weight texture, guiding the algorithm to focus on the most important regions.

## Animator

Animations are exported as a sequence of images, therefore using a tool such as [ffmpeg](https://www.ffmpeg.org/) is required in order to generate a video or gif.

| Timeline | Scale all | Translate from top | Wave from left |
| :-------------------------------------------------------------------: | :--------------------------------------------------------------------: | :------------------------------------------------------------------------: | :-------------------------------------------------------------------------: |
| | | | |

## Settings

Genart provides an extensive range of configurable settings, allowing users to adjust the attributes of its algorithms through a dedicated interface. Additionally, pre-tested presets are available to produce high-quality results, offering a practical option for users who may not have prior knowledge of the underlying algorithms.

## Installation

Genart is available through the following options:

- [Itch.io](https://franco-yudica.itch.io/genart)
- The latest [GitHub release](https://github.com/FrancoYudica/Genart/releases)
- Building the project locally using [Godot 4.3](https://godotengine.org/download).

## Remaining tasks

### Multithreaded individual generator

Genart prioritizes offering a wide range of creative control over raw performance. While this focus enables extensive customization, it may come at the cost of speed. Implementing multithreading within the individual generator algorithms will address this by enhancing responsiveness and overall user experience.

## Gallery

Some examples with different images as building blocks.

| Mona Lisa | Billie Eilish |
| :------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------: |
| _Mona Lisa. 300 fixed rotation capsules_ | _Billie Eilish. 500 brush strokes_ |

| | |
| :-----------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------: |
| _Lamborghini Aventador. 200 geometric rounded objects_ | _Milky Way. 200 glow objects_ |

## Contributing

Contributions of all kinds are welcome! If you’re interested in contributing to this project, please take a moment to review [`CONTRIBUTING.md`](https://github.com/FrancoYudica/Genart/blob/main/CONTRIBUTING.md) file.