# generative art

Generative art is art created in whole or in part with autonomous systems, commonly using algorithms, code, and procedural rules to produce visual or other artistic outputs.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Attention of a Kiss: Generative Video Attention Maps as Explainable and Creative Material

DevFeed: [Attention of a Kiss: Generative Video Attention Maps as Explainable and Creative Material](<https://devfeed.tech/articles/attention-of-a-kiss-generative-video-attention-maps-as-explainable-and-creative-material-137230.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.05323>)

Author: Adam Cole, Mick Grierson

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analog](<https://devfeed.tech/tags/analog.md>), [arts](<https://devfeed.tech/tags/arts.md>), [attention](<https://devfeed.tech/tags/attention.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [creative](<https://devfeed.tech/tags/creative.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-transformers](<https://devfeed.tech/tags/diffusion-transformers.md>), [explainable-ai](<https://devfeed.tech/tags/explainable-ai.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative-video](<https://devfeed.tech/tags/generative-video.md>), [maps](<https://devfeed.tech/tags/maps.md>), [medium](<https://devfeed.tech/tags/medium.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

The paper proposes a tool built on the open-source Wan model to extract and visualize cross-attention maps in text-to-video generation, making attention's temporal and spatial behavior available for inspection. Through exploratory probes and artistic case studies, the authors consider the maps both as analytical material and as a creative medium. The supplied excerpt does not specify implementation details or report particular findings from the case studies.

### Source excerpt

arXiv:2509.05323v3 Announce Type: replace Abstract: This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study proposes a method for extracting and visualizing cross-attention maps in generative video models. Built on the open-source Wan model, our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation. Through exploratory probes and a series of artistic case studies, we examine the potential of attention maps as both analytical tools and raw artistic material. This work contributes to the growing field of Explainable AI for the Arts (XAIxArts), inviting artists to reclaim the inner workings of AI as a creative medium.

## Evolutionary Computation: A Paradigm of Natural Generative AI and Creative Synthesis

DevFeed: [Evolutionary Computation: A Paradigm of Natural Generative AI and Creative Synthesis](<https://devfeed.tech/articles/evolutionary-computation-a-paradigm-of-natural-generative-ai-and-creative-synthesis-128489.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.08590>)

Author: Abhishek Gupta, Yaxin Shi, Ying Wu, Melvin Wong, Ivor Tsang, Thiago Rios, Stefan Menzel, Bernhard Sendhoff, Yaqing Hou, Yew-Soon Ong

Published: 2026-11-11T05:00:00Z

Content type: opinion

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [creative](<https://devfeed.tech/tags/creative.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [selection](<https://devfeed.tech/tags/selection.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>)

### AI overview

The paper argues that evolutionary computation could support creative synthesis through stochastic variation, diversification, and selection. It distinguishes parent-centric operators, which induce population distributions resembling conventional generative models, from disruptive operators that can make structured leaps to out-of-distribution artifacts. It identifies a product-of-distributions structure in certain disruptive multitask EC variations and reports a similar structure in a local second-order approximation of a generative adversarial program for creative extrapolation. The authors argue that multiple fitness landscapes moderate selection pressure, helping novel artifacts survive and seed further innovation. This is a position paper proposing principles for open-ended exploration, not a specific algorithmic implementation.

### Source excerpt

arXiv:2510.08590v2 Announce Type: replace-cross Abstract: Generative AI relies on statistical learning and local gradient-based guidance, often resulting in artifacts that may be more emulative than genuinely creative. This position paper advances a perspective on Evolutionary Computation (EC) as a paradigm of Natural Generative AI (NGAI), in which stochastic variation, diversification, and natural selection present an alternative foundation for generative exploration and creative synthesis. EC provides an array of variation operators with varied generative capabilities: parent-centric operators induce population distributions analogous to conventional generative models, while disruptive operators can produce structured evolutionary leaps to out-of-distribution artifacts (e.g., programs, designs, or AI agents themselves). This lens reveals a unique theoretical association between certain disruptive variations in multitask EC and a product-of-distributions population structure. A mathematical result derived herein shows that a product structure also occurs under a local second-order approximation of an established generative adversarial program for creative extrapolation, inspired by Martindale's cognitive theory of artistic creation. The simultaneous existence of multiple fitness landscapes in multitask EC inherently moderates selection pressure, allowing these novel artifacts to survive and seed further innovation. Structured disruption and selection moderation are thus argued to be key elements to support creative synthesis. Agnostic to any specific algorithmic realization, the perspective positions NGAI as an emerging engine for open-ended scientific exploration.

## Art in Humanity's Code

DevFeed: [Art in Humanity's Code](<https://devfeed.tech/articles/art-in-humanity-s-code-127198.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.05174>)

Author: Benoit Baudry, Yogya Gamage, Nadia Gonzalez Fernandez, Lena MK, Roxana Pena Mendieta, Rafaela Souza Pinter, Stefano Zacchiroli

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [creative technology](<https://devfeed.tech/topics/creative-technology.md>), [Digital Public Good](<https://devfeed.tech/topics/digital-public-goods.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [art](<https://devfeed.tech/tags/art.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [contributor](<https://devfeed.tech/tags/contributor.md>), [creative](<https://devfeed.tech/tags/creative.md>), [creative-coding](<https://devfeed.tech/tags/creative-coding.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [designers](<https://devfeed.tech/tags/designers.md>), [digital](<https://devfeed.tech/tags/digital.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [education](<https://devfeed.tech/tags/education.md>), [educators](<https://devfeed.tech/tags/educators.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [industries](<https://devfeed.tech/tags/industries.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [processing](<https://devfeed.tech/tags/processing.md>), [public](<https://devfeed.tech/tags/public.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [university](<https://devfeed.tech/tags/university.md>)

### AI overview

The study analyzes 1,613,571 public repositories using artist-led creative coding libraries, collected from the Software Heritage archive, to examine where and how code-based creative practices are used. Its quantitative and qualitative findings show generative art and creative coding across the world, with adoption in education and creative industries. Examples and contributor profiles range from university curricula to contemporary art. The abstract presents the work as a foundation for further research into diversity in code and creative practice.

### Source excerpt

arXiv:2608.05174v2 Announce Type: replace-cross Abstract: Artist-led open-source libraries such as Processing or openFrameworks have had a major impact on artists and designers who use code as a creative medium. In this work, we conduct the first large-scale empirical study of public code repositories that use these libraries. Our study dives into 1,613,571 code repositories collected from the Software Heritage archive. Combining quantitative and qualitative methods, we investigate the diversity of practices and practitioners in terms of code hosting, geographical distribution, characteristics of code-based creative works and the purposes of these works. Key findings include evidence of the worldwide presence of generative art and creative coding, as well as the adoption of these practices in both education and across creative industries. We illustrate these findings with concrete examples of repositories and contributor profiles around the globe, spanning the spectrum from university curricula to contemporary art. These results lay the groundwork for educators, researchers, and artists who investigate code and creative practices to foster sustained diversity in the construction of our digital world.

## Pressing Enter Doesn't Make You a Creator

DevFeed: [Pressing Enter Doesn't Make You a Creator](<https://devfeed.tech/articles/pressing-enter-doesn-t-make-you-a-creator-122683.md>)

Original publisher: [Read original article](<https://hackernoon.com/pressing-enter-doesnt-make-you-a-creator?source=rss>)

Author: Bj Beyond

Published: 2026-11-08T18:00:03Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistance](<https://devfeed.tech/tags/ai-assistance.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-ethics](<https://devfeed.tech/tags/ai-ethics.md>), [application](<https://devfeed.tech/tags/application.md>), [argument](<https://devfeed.tech/tags/argument.md>), [art](<https://devfeed.tech/tags/art.md>), [article](<https://devfeed.tech/tags/article.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [authorship](<https://devfeed.tech/tags/authorship.md>), [automation](<https://devfeed.tech/tags/automation.md>), [beautiful](<https://devfeed.tech/tags/beautiful.md>), [beginner](<https://devfeed.tech/tags/beginner.md>), [build](<https://devfeed.tech/tags/build.md>), [business](<https://devfeed.tech/tags/business.md>), [button](<https://devfeed.tech/tags/button.md>), [camera](<https://devfeed.tech/tags/camera.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [creative](<https://devfeed.tech/tags/creative.md>), [creativity](<https://devfeed.tech/tags/creativity.md>), [critical-thinking](<https://devfeed.tech/tags/critical-thinking.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [human-ai-collaboration](<https://devfeed.tech/tags/human-ai-collaboration.md>), [human-creativity](<https://devfeed.tech/tags/human-creativity.md>)

### AI overview

The article argues that generative AI lowers barriers to making things, but pressing Enter does not by itself confer creative skill or understanding. Its central distinction is between accepting a polished output and exercising judgment: questioning its meaning and reliability, revising it, and taking responsibility for what is published. It cites research suggesting a tradeoff: AI assistance can improve individuals' story ratings while making outputs more similar, narrow idea diversity in brainstorming, and introduce fewer new ideas in GPT-4-assisted admissions essays under the studied conditions. The author presents these findings as reasons to preserve human judgment, not proof that AI cannot be original or that human-made work is inherently better. AI can help people learn, express ideas, and explore possibilities; the concern is stopping at the first convincing result and substituting generation for thought.

### Source excerpt

AI can generate almost anything. But somewhere along the way, we started confusing the ability to produce with the ability to create.

## Behind the Blog: Dam's Bursting

DevFeed: [Behind the Blog: Dam's Bursting](<https://devfeed.tech/articles/behind-the-blog-dam-s-bursting-121636.md>)

Original publisher: [Read original article](<https://www.404media.co/behind-the-blog-dams-bursting/>)

Author: Samantha Cole

Published: 2026-11-06T17:12:55Z

Content type: opinion

Language: en

Sources: [404 Media](<https://devfeed.tech/sources/404-media.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [art](<https://devfeed.tech/tags/art.md>), [audio](<https://devfeed.tech/tags/audio.md>), [behind-the-blog](<https://devfeed.tech/tags/behind-the-blog.md>), [behind-the-scenes](<https://devfeed.tech/tags/behind-the-scenes.md>), [code](<https://devfeed.tech/tags/code.md>), [election](<https://devfeed.tech/tags/election.md>), [electronic](<https://devfeed.tech/tags/electronic.md>), [electronic-music](<https://devfeed.tech/tags/electronic-music.md>), [generative](<https://devfeed.tech/tags/generative.md>), [jitter](<https://devfeed.tech/tags/jitter.md>), [max](<https://devfeed.tech/tags/max.md>), [msp](<https://devfeed.tech/tags/msp.md>), [music](<https://devfeed.tech/tags/music.md>), [programming](<https://devfeed.tech/tags/programming.md>), [programming-language](<https://devfeed.tech/tags/programming-language.md>), [synthesizers](<https://devfeed.tech/tags/synthesizers.md>)

### AI overview

Joseph describes Max/MSP as a visual programming language used in music and visual art, where building tools can require substantial effort to understand how components fit together. He has used it to generate randomized drum-and-bass breaks from a drum break, create evolving synthesizer sounds modeled on Tibetan singing bowls, and begin using its Jitter component to generate visuals from audio. The excerpt opens with a reaction to someone using Claude with Max, but gives no details about that process or its results.

### Source excerpt

This week, we discuss election outcomes and code as a human endeavor.

## Sweary plots, DOOM maps, postcards and more #ArtTuesday

DevFeed: [Sweary plots, DOOM maps, postcards and more #ArtTuesday](<https://devfeed.tech/articles/sweary-plots-doom-maps-postcards-and-more-arttuesday-114212.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/03/sweary-plots-doom-maps-postcards-and-more-arttuesday/>)

Author: Anne Barela

Published: 2026-11-03T14:05:30Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [accordion](<https://devfeed.tech/tags/accordion.md>), [art](<https://devfeed.tech/tags/art.md>), [arttuesday](<https://devfeed.tech/tags/arttuesday.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cables](<https://devfeed.tech/tags/cables.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [handwriting](<https://devfeed.tech/tags/handwriting.md>), [paper](<https://devfeed.tech/tags/paper.md>), [pen-plotting](<https://devfeed.tech/tags/pen-plotting.md>), [plotting](<https://devfeed.tech/tags/plotting.md>), [printing](<https://devfeed.tech/tags/printing.md>), [projects](<https://devfeed.tech/tags/projects.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Daniel Catt's generative handwriting plotter builds organic page structures in five stages: it lays out rows and interacting lines, grows new lines from that skeleton, removes sections with Perlin-noise-distorted rectangles to restore negative space, fills the remaining lines with random or supplied letters, and adds cables between letter clusters. Catt says he wrote the code by hand, having previously built the components separately. He has used the results on postcards and accordion books and wants to scale them up onto Saunders Waterford watercolour paper. The text also briefly mentions his studio's 3D clay printing, described as pen plotting with a Z-axis.

### Source excerpt

Daniel Catt writes in his newsletter about a new generative system for plotted handwriting art, one that moves away from the rigid magazine style grids he has used before and toward something more organic. The system runs in five stages. "Foundation" splits the page into 3 to 24 rows and draws horizontal lines that attract [...]

## She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery

DevFeed: [She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery](<https://devfeed.tech/articles/she-works-he-works-a-curious-exploration-of-gender-bias-in-ai-generated-imagery-102903.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2407.18524>)

Author: Amalia Foka

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Image](<https://devfeed.tech/topics/image.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [art](<https://devfeed.tech/tags/art.md>), [artwork](<https://devfeed.tech/tags/artwork.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [culture](<https://devfeed.tech/tags/culture.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [gender](<https://devfeed.tech/tags/gender.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [theory](<https://devfeed.tech/tags/theory.md>), [women](<https://devfeed.tech/tags/women.md>), [workers](<https://devfeed.tech/tags/workers.md>)

### AI overview

The project compares text-to-image depictions of male and female construction workers using prompts that mix gendered traits with unconventional contexts. It reports that women are more often represented through aesthetics and agility, while men are associated with authority and professionalism. Drawing on feminist visual theory, it treats AI imagery as both a reflection of cultural stereotypes and a means to critique them. The abstract calls for transparent practices, diverse datasets and reflexive engagement with AI's cultural impact; the supplied text does not specify which image-generation systems were tested or provide detailed methods or results.

### Source excerpt

arXiv:2407.18524v2 Announce Type: replace-cross Abstract: She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in AI-generated imagery. By juxtaposing text-to-image outputs of male and female construction workers, it reveals how societal biases manifest in generative AI systems. The study employs critically crafted prompts that blend traditionally gendered traits with unconventional contexts, exposing disparities in representation-emphasizing aesthetics and agility for women versus authority and professionalism for men. Grounded in Griselda Pollock's feminist insights on visual culture, the project positions AI as both a technological and cultural actor, capable of perpetuating stereotypes and enabling critique. As both a study and an artwork, the project underscores the transformative potential of AI to reimagine gender norms and inspire equitable narratives. It highlights the ethical implications of AI in creative industries, calling for transparent practices, diverse datasets, and reflexive engagement with AI's cultural impact. Through its integration of critical analysis and artistic exploration, She Works, He Works contributes to broader discussions on inclusive AI development and the role of art in fostering societal change. This dual approach showcases the power of AI as a medium for critique and a tool for envisioning more just and inclusive futures.

## Type a Formula, Render Art: Build an Interactive Fractal Generator in 2026

DevFeed: [Type a Formula, Render Art: Build an Interactive Fractal Generator in 2026](<https://devfeed.tech/articles/type-a-formula-render-art-build-an-interactive-fractal-generator-in-2026-98468.md>)

Original publisher: [Read original article](<https://hackernoon.com/type-a-formula-render-art-build-an-interactive-fractal-generator-in-2026?source=rss>)

Author: Joe bou khalil

Published: 2026-10-23T20:35:53Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [interactive web design](<https://devfeed.tech/topics/interactive-web-design.md>)

Tags: [art](<https://devfeed.tech/tags/art.md>), [aspect](<https://devfeed.tech/tags/aspect.md>), [beautiful](<https://devfeed.tech/tags/beautiful.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [color](<https://devfeed.tech/tags/color.md>), [created](<https://devfeed.tech/tags/created.md>), [css](<https://devfeed.tech/tags/css.md>), [data](<https://devfeed.tech/tags/data.md>), [demo](<https://devfeed.tech/tags/demo.md>), [digital](<https://devfeed.tech/tags/digital.md>), [digital-art](<https://devfeed.tech/tags/digital-art.md>), [display](<https://devfeed.tech/tags/display.md>), [download](<https://devfeed.tech/tags/download.md>), [drawing](<https://devfeed.tech/tags/drawing.md>), [fractal-art](<https://devfeed.tech/tags/fractal-art.md>), [fractal-generator](<https://devfeed.tech/tags/fractal-generator.md>), [generator](<https://devfeed.tech/tags/generator.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [html](<https://devfeed.tech/tags/html.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [mathematics](<https://devfeed.tech/tags/mathematics.md>), [project](<https://devfeed.tech/tags/project.md>), [render](<https://devfeed.tech/tags/render.md>), [view](<https://devfeed.tech/tags/view.md>)

### AI overview

The project is a browser based fractal laboratory where users edit a formula such as `z^2 + c`, choose Mandelbrot style (vary c) or Julia (fixed c, vary z), set iteration count and a color palette, then render and zoom by clicking the canvas. It uses Math.js to evaluate the formula for each pixel, iterating until the value's magnitude exceeds 2 or the iteration limit is reached. The app provides PNG and SVG download buttons, though the SVG export embeds the rendered PNG as an image rather than vector paths. The article presents it as a simple tool for exploring mathematical patterns and creating artwork.

### Source excerpt

View the code and try it yourself. Whatever your opinion of using this project fractal art generator is, it is available here.

## Creative Prompting with Disco Diffusion: Voronoi Noise Inits on Runpod

DevFeed: [Creative Prompting with Disco Diffusion: Voronoi Noise Inits on Runpod](<https://devfeed.tech/articles/creative-prompting-with-disco-diffusion-voronoi-noise-inits-on-runpod-94554.md>)

Original publisher: [Read original article](<https://www.runpod.io/blog/disco-diffusion-voronoi-noise-runpod>)

Author: Zhen Lu

Published: 2026-10-22T02:42:59Z

Content type: tutorial

Language: en

Sources: [Runpod Blog.](<https://devfeed.tech/sources/runpod-blog.md>)

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>), [creative coding](<https://devfeed.tech/topics/creative-coding.md>), [Graphics](<https://devfeed.tech/topics/graphics.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amazing](<https://devfeed.tech/tags/amazing.md>), [article](<https://devfeed.tech/tags/article.md>), [based](<https://devfeed.tech/tags/based.md>), [blog](<https://devfeed.tech/tags/blog.md>), [box](<https://devfeed.tech/tags/box.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [explore](<https://devfeed.tech/tags/explore.md>), [noise](<https://devfeed.tech/tags/noise.md>), [post](<https://devfeed.tech/tags/post.md>), [setup](<https://devfeed.tech/tags/setup.md>), [this](<https://devfeed.tech/tags/this.md>), [tips](<https://devfeed.tech/tags/tips.md>), [unique](<https://devfeed.tech/tags/unique.md>), [using](<https://devfeed.tech/tags/using.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The excerpt describes using Voronoi noise instead of Disco Diffusion's default Perlin noise as a render's starting input. Add `init_generator: voronoi` and `voronoi_points: 100` to the config; increasing `skip_steps` to about 20% of total steps can make the starting pattern more prominent, though the setting is adjustable. More Voronoi points create smaller regions. Colors can be assigned from a fixed `static` palette or randomly generated within configured RGB bounds; the shown default generated bounds favor blue. The post update says the discoart template no longer includes this feature, so users can instead generate a Voronoi image separately and use it as an init image. The excerpt reports differing results with Voronoi versus Perlin, with and without a secondary model, but does not provide enough detail to characterize those outputs.

### Source excerpt

Explore a unique artistic technique using Voronoi noise inits with Disco Diffusion on Runpod. This post walks through setup and tips for generating.

## Turn Any Photo Into Retro ASCII Art in Seconds

DevFeed: [Turn Any Photo Into Retro ASCII Art in Seconds](<https://devfeed.tech/articles/turn-any-photo-into-retro-ascii-art-in-seconds-63345.md>)

Original publisher: [Read original article](<https://webdesignerdepot.com/turn-any-photo-into-retro-ascii-art-in-seconds/>)

Author: Alex Harper

Published: 2026-10-01T14:19:00Z

Content type: article

Language: en

Sources: [Web Designer Depot](<https://devfeed.tech/sources/web-designer-depot.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [shape-aware rendering](<https://devfeed.tech/topics/shape-aware-rendering.md>), [ASCII dithering](<https://devfeed.tech/topics/ascii-dithering.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [ascii](<https://devfeed.tech/tags/ascii.md>), [ascii-art](<https://devfeed.tech/tags/ascii-art.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-tools](<https://devfeed.tech/tags/browser-tools.md>), [creative-tools](<https://devfeed.tech/tags/creative-tools.md>), [design-resources](<https://devfeed.tech/tags/design-resources.md>), [digital-art](<https://devfeed.tech/tags/digital-art.md>), [graphic-design](<https://devfeed.tech/tags/graphic-design.md>), [image-converter](<https://devfeed.tech/tags/image-converter.md>), [retro-design](<https://devfeed.tech/tags/retro-design.md>), [tool](<https://devfeed.tech/tags/tool.md>), [typography](<https://devfeed.tech/tags/typography.md>), [visual-ui-design](<https://devfeed.tech/tags/visual-ui-design.md>), [web-tools](<https://devfeed.tech/tags/web-tools.md>)

### AI overview

Image to ASCII is a free browser-based tool that converts photos into ASCII art with adjustable visual settings and presets for logos, portraits, social posts, and other uses. Images are processed locally in the browser, and results can be copied or exported in several formats. GIFs convert to still images.

### Source excerpt

Turn any photo into gloriously retro ASCII art -- made entirely from letters, symbols, and tiny bits of chaos. This free tool turns your dog, face, logo, or worst holiday photo into something that belongs on a 1980s terminal. You will absolutely waste 10 minutes on it.

## Behind "ANCESTRA": combining Veo with live-action filmmaking

DevFeed: [Behind "ANCESTRA": combining Veo with live-action filmmaking](<https://devfeed.tech/articles/behind-ancestra-combining-veo-with-live-action-filmmaking-6141.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/behind-ancestra-combining-veo-with-live-action-filmmaking/>)

Author: Kory Mathewson

Published: 2025-10-25T17:27:10Z

Content type: article

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Image](<https://devfeed.tech/topics/image.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-model](<https://devfeed.tech/tags/3d-model.md>), [actor](<https://devfeed.tech/tags/actor.md>), [added](<https://devfeed.tech/tags/added.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-generated-images](<https://devfeed.tech/tags/ai-generated-images.md>), [also](<https://devfeed.tech/tags/also.md>), [amazing](<https://devfeed.tech/tags/amazing.md>), [area](<https://devfeed.tech/tags/area.md>), [array](<https://devfeed.tech/tags/array.md>), [art](<https://devfeed.tech/tags/art.md>), [film](<https://devfeed.tech/tags/film.md>), [filmmaking](<https://devfeed.tech/tags/filmmaking.md>), [live](<https://devfeed.tech/tags/live.md>), [make](<https://devfeed.tech/tags/make.md>), [none](<https://devfeed.tech/tags/none.md>), [people](<https://devfeed.tech/tags/people.md>), [team](<https://devfeed.tech/tags/team.md>), [using](<https://devfeed.tech/tags/using.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

"ANCESTRA" combines live-action filmmaking with AI-generated imagery and video. Gemini turned family photos into detailed prompt descriptions; Imagen produced concept art and reference images; Veo animated images, matched camera or subject motion from draft videos, and added a generated newborn to live-action footage while keeping the rest of the scene consistent. The team fine-tuned Imagen for consistent art direction, then refined generated shots with traditional VFX and color grading. The article says Veo enabled complex motion-led sequences in minutes, while text prompts alone offered limited motion control; it does not quantify production time or compare overall quality with other methods. More than 200 filmmaking and production experts contributed.

### Source excerpt

We partnered with Darren Aronofsky, Eliza McNitt and a team of more than 200 people to make a film using Veo and live-action filmmaking.

## A Review of Generative Art, Blogging, Work, and Side Projects in 2021

DevFeed: [A Review of Generative Art, Blogging, Work, and Side Projects in 2021](<https://devfeed.tech/articles/into-2022-37290.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/into-2022/>)

Author: Stanko

Published: 2022-03-04T00:00:00Z

Content type: opinion

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [pixel](<https://devfeed.tech/topics/pixel.md>), [ibm](<https://devfeed.tech/topics/ibm.md>)

Tags: [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [clients](<https://devfeed.tech/tags/clients.md>), [code](<https://devfeed.tech/tags/code.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [pixel](<https://devfeed.tech/tags/pixel.md>)

### AI overview

The author reviews 2021, covering generative art, reduced blogging activity, a redesign of the site from Jekyll to Zola, work with TED and IBM Research, and side projects including 3D modeling, electronics, and a pixel art frame.

### Source excerpt

I'm super late with this post, but again, better late than never. I just couldn't find the inspiration and drive for writing last year. Generally, I lacked motivation and wasn't really productive. Generative Art # As for my art, 2021 wasn't as fruitful as the year before, but I did finish a couple of drawings. I'm still very much into it and lately I have found my drive again. AxiDraw, the pen plotter, continues to be my favorite purchase ever. Here are a couple of my plotted drawings from the last year: I wrote a separate post about the creative process behind the last drawing - Breaking down Krypton. Blog # Oh boy, did I neglect this blog last year. I wrote only four posts. But I really couldn't find the inspiration and will to write. Naturally, the number of visits dropped, and it was a little above 90K. The fact that adblockers now block Goat Analytics also had an impact on numbers. Luckily, now I have way more drive to write and keep the site updated. This February, the blog got a redesign that I planned for a long time. I wanted to add "Art" and "Projects" sections, but I kept redesigning it over and over again. Finally, when I decided to switch from JekyllI'll probably cover that in a another post. to Zola I was able to focus and finish the redesign. I did the design myself, using the thing or two I picked up from my designer colleagues. I released it as soon as I had something presentable. It was super bare bones and I'm still tweaking it and adding more personality, but nonetheless, I'm pretty satisfied with how it turned out. Fun fact, you can try my layout debug mode, I kept it in the production on purpose. Work # Last year was productive for my company as a whole. I had the pleasure of working with two clients, TED and IBM Research. In both cases, teams consisted of wonderful people and I feel proud that I was able to help them build and improve their digital products. Side projects # I tremendously enjoy these small pet projects. Generative art was a bi

## Breaking down Krypton

DevFeed: [Breaking down Krypton](<https://devfeed.tech/articles/breaking-down-krypton-37246.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/breaking-down-krypton/>)

Author: Stanko

Published: 2022-03-01T00:00:00Z

Content type: article

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [browser](<https://devfeed.tech/topics/browser.md>)

Tags: [ascii](<https://devfeed.tech/tags/ascii.md>), [browser](<https://devfeed.tech/tags/browser.md>), [diagram](<https://devfeed.tech/tags/diagram.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

### AI overview

This article breaks down how "Krypton," a generative artwork, was created. It discusses the author's JavaScript, p5.js, and custom tooling, including parameter controls, browser-history-based iteration, and the use of Voronoi diagrams to generate the drawing.

### Source excerpt

This post was originally written for our internal technology newsletter at Work & Co. It is a little bit adapted for web, but the content is almost identical. About a year ago I made this plot. It is called "Krypton"Named by a dear friend and ex-colleague, and I'll try to break down how it was made. The wonderful thing about generative art is that code is just a tool. Thing that really matters is the actual artwork. In this specific case, code is straightforward and relatively simple. But it produces drawings that, in my opinion, look visually pleasing and have a nice sense of depth to them. Tooling # For all of my generative work, I use plain JavaScript, p5.js and a couple of custom-made tools. These tools are often crude, but they do exactly what I want so I don't mind. With each new project I keep adding more features and polishing them. At some point these tools may reach the point where they are presentable. If that happens I'll gladly share them with the world and open source everything. This is how the interface looks. I have an easy way to add controls for image parameters. These controls allow me to tweak drawings with a short feedback loop. Each time a parameter is changed, the image is redrawn and the parameter is reflected in the URL. This allows me to go through iterations using the browser history. To make navigation through the history easier, for each unique combination of parameters, I generate a random color and ASCII face. That is why my browser history looks like this :) Voronoi diagram # I use Voronoi diagrams a lot in my drawings. So much, that I'm sometimes trying to avoid them, to make sure I'm not limiting myself to a single algorithm. Voronoi diagram takes a collection of points, and then partitions a plane into polygons, where each polygon's edge is right in the middle of two points. It sounds like a lot, but if you study this image, it should become clearer. For a more detailed explanation you can check out the article on Wikipedia. Gener

## Libraries I use for generative art

DevFeed: [Libraries I use for generative art](<https://devfeed.tech/articles/libraries-i-use-for-generative-art-37303.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/js-libraries-for-generative-art/>)

Author: Stanko

Published: 2022-02-28T00:00:00Z

Content type: article

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Randomizer](<https://devfeed.tech/topics/randomizer.md>), [plotting](<https://devfeed.tech/topics/plotting.md>), [WebAssembly](<https://devfeed.tech/topics/web-assembly.md>), [Data structures](<https://devfeed.tech/topics/data-structures.md>)

Tags: [generative-art](<https://devfeed.tech/tags/generative-art.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [plotting](<https://devfeed.tech/tags/plotting.md>), [programming](<https://devfeed.tech/tags/programming.md>), [random](<https://devfeed.tech/tags/random.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>)

### AI overview

A curated list of JavaScript libraries used to create generative art, organized into categories including randomness and noise, geometry, vector fields, 3D, spatial data structures, Axidraw, and other tools. The author selected the libraries based partly on performance and describes their practical uses.

### Source excerpt

This is going to be a very straight forward post. Just a list of JavaScript libraries I use in creating my generative art. And I really mean I use (and abuse) them. All of them are used in multiple of my drawings. I'll include couple of photos under the respective libraries. I finally settled with these libraries after trying several other alternatives for each. Performance was one of the key factors (especially as generative work can get brute-forcy sometimes). Huge thank you to all people who created and shared these wonderful tools!Also, as a rule of thumb, when you find a good library, you might want to check author's GitHub profile. In the most cases you are going to find more useful stuff there. That is exactly how I found some of these. Categories: Randomness and noise Geometry Vector fields 3D vector line engines Spatial data structures Axidraw Other Randomness and noise # seedrandom # In generative programming it is super important to be able to repeat the same output. As randomness is heavily involved, we need a way to repeat random values. That's where seedrandom steps in as an excellent seeded random number generator. random-words # For random number generator seeds, I like to use real words instead of randomly generated strings. This library is a simple dictionary of couple of thousands english words. simplex-noise # Fast implementation of Open Simplex noise. poisson-disk-sampling # When you need a random collections of points in space, Poisson sampling is a great tool. It gives us much more natural distribution than just using random values. Geometry # js-angusj-clipper # This library is a lifesaver. For all your polygon clipping and offseting needs. And it is super fast as it is implemented in WebAssembly. voronoi # Sometimes I think I use Voronoi diagrams too much in my work. Anyway, this library efficiently computes Voronoi diagrams. robust-point-in-polygon # For figuring out if the point is inside of the polygon. I tried a couple of other libraries

## From JavaScript to paper: a linocut adventure

DevFeed: [From JavaScript to paper: a linocut adventure](<https://devfeed.tech/articles/from-javascript-to-paper-a-linocut-adventure-35549.md>)

Original publisher: [Read original article](<https://meowni.ca/posts/tree-rings/>)

Author: Monica Dinculescu

Published: 2021-04-28T00:00:00Z

Content type: article

Language: en

Sources: [Monica Dinculescu](<https://devfeed.tech/sources/monica-dinculescu.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>)

Tags: [art](<https://devfeed.tech/tags/art.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [paper](<https://devfeed.tech/tags/paper.md>)

### AI overview

The author describes creating generative art inspired by tree rings and translating the result into a paper linocut. The process combines observations about how tree rings record a tree's history with JavaScript-generated patterns and physical carving.

### Source excerpt

One of my favourite kinds of art to make involves taking nature and seeing it as simple shapes. Buildings are cubes, flowers are circles, hills are curves. Shells are spirals. Tree rings are weird circle bois, and they are some of the best. I've wanted to make a generative art of a tree ring for a long time, but everything I made kept sucking (scroll to the bottom if you don't believe me. Shit was bad bad). I finally made something I like, I thought it might be neat to write a little bit about The Process™, since it involves both JavaScript and murderous little knives. Let's talk trees My friend Kyle has a ranch, and in the summer he lets his friends fulfill the burned out millenial dream of having no cell signal and sleeping in a tent. He has infinitely many trees, and sometimes he lets me do a craft with some of the trees he chops down. I'm "currently" (read: I started last year and I'll probably finish in 2026) making a side table. I also made these coasters: Trees are rad, yo. Young trees have very regular and evenly spaced rings because much like human children, they haven't had a lot of life to live. However, as trees get older, they get jobs they don't like, have to start making dinner every night, start having back pains from literally just being trees and their rings get wonkier. Here is what I'm making my table from: Trees can grow unevenly because of droughts or insects or capitalism building shit where it shouldn't. They get visible scars from forest fires. You can map the entire life of a tree (and tbh, of everything that was happening around the tree) by looking at its cross section. There's something called a ghost forest that indicates at some point, something happened (like an earthquake), which caused salt water to rise, killing all the trees that lived there. Here's a photo (ref) of a knotty tree (heh heh) that has fire scars: So you know, if you want a tree ring, you can't just draw some concentric circles and call it a day. Generate some tree r

## Week 8: Selling Generative Art Prints and Running an Online Store

DevFeed: [Week 8: Selling Generative Art Prints and Running an Online Store](<https://devfeed.tech/articles/week-8-35578.md>)

Original publisher: [Read original article](<https://meowni.ca/posts/week-8>)

Author: Monica Dinculescu

Published: 2021-02-27T00:00:00Z

Content type: opinion

Language: en

Sources: [Monica Dinculescu](<https://devfeed.tech/sources/monica-dinculescu.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [Software](<https://devfeed.tech/topics/software.md>), [stripe](<https://devfeed.tech/topics/stripe.md>), [OAuth](<https://devfeed.tech/topics/oauth.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>)

Tags: [generative-art](<https://devfeed.tech/tags/generative-art.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [software](<https://devfeed.tech/tags/software.md>), [stripe](<https://devfeed.tech/tags/stripe.md>)

### AI overview

A personal weekly reflection about opening an online store for generative art prints, selling out of two kinds of prints, and using BigCartel, Stripe, and PirateShip for ecommerce and shipping. It also briefly covers fitness challenges and painting on an iPad.

### Source excerpt

This week was entirely consumed by the fact that I opened an online store to sell generative "art" prints. Art is in quotations here because I have a deeply unhealthy relationship with calling anything I do art, or myself an artist, but we don't have time to for a therapy session right now. It went really great. I sold out of 2 kinds of prints! People who weren't just my friends put it orders! My first customer ever was Mariko, which is absurd because she should've gotten a free print without even asking based on the kilograms of gacha she's brought me from Japan, but of course she was also the first one to see the tweet about the store because that's just the kind of friend she is. (this paragraph is really niche and boring, skip it). Every once in a while I use a software that blows my fucking mind. E-commerce is generally NOT this experience btw, because it's all integrations that are 90% magic and 10% wonky af. Like, my store is a BigCartel store (big fan!), but the site itself is a bit flaky so sometimes Things Will Happen™ (like pages won't redirect, the theme editor will just panic, javascript is a prison). Stripe was like 95% magic and 5% "the oauth flow didn't redirect well For Reasons™ so I had to do it twice". I don't even know who was at fault there. Anyway, PirateShip is a thing that prints USPS labels and it was 120% magic. People wrote their addresses in their orders in my store; I clicked a single button on the PirateShip site, which imported those addresses, made shipping labels, made customs forms for the international orders, formatted all the labels for my label printer to print AND emailed all the customers their tracking numbers. And charged me 0 extra dollars. PirateShip, I don't know how you make your money but you are an absolute gem and I love you. The post office gentleman even commented on how together my shit was. Frances and I had a FitBit active minutes challenge and I WON by like 32 minutes (aka extremely close). Zach was also in some

## A 2020 Review of Generative Art, Blogging, Analytics, and Working From Home

DevFeed: [A 2020 Review of Generative Art, Blogging, Analytics, and Working From Home](<https://devfeed.tech/articles/into-2021-37289.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/into-2021/>)

Author: Stanko

Published: 2021-02-01T00:00:00Z

Content type: opinion

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [Google Analytics](<https://devfeed.tech/topics/google-analytics.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [art](<https://devfeed.tech/tags/art.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [google-analytics](<https://devfeed.tech/tags/google-analytics.md>), [instagram](<https://devfeed.tech/tags/instagram.md>), [macos](<https://devfeed.tech/tags/macos.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [windows](<https://devfeed.tech/tags/windows.md>), [working-from-home](<https://devfeed.tech/tags/working-from-home.md>)

### AI overview

A personal review of 2020 covering the author's progress in generative art and pen plotting, changes from Google Analytics to GoatCounter, blog traffic and redirects, and working from home.

### Source excerpt

2020 was a hard one. I started writing this post in December, but I couldn't make myself finish it. The whole situation with COVID made me anxious at times and I didn't really have motivation for my side projects including this blog. But I won't focus on bad things, everyone had a tough year, so let's try to stay positive. Generative Art # I had one huge positive this year - I got into generative art. My fiance likes to say that I woke up on the first on January and started drawing some triangles. Triangles were super naive, but I'm super happy with my progress and these are some of my creations (all pen plotted): Special thanks to Vladimir Mitrović who was the only person I knew doing generative art. When I reached out, he selflessly helped me start with the whole thing. Be sure to visit his website as he is doing amazing stuff. I already wrote about my generative work a little, but I will create a separate site section for my artwork. Meanwhile, you can see the most of my work on Instagram. I'm super thrilled that people like my art enough to hang it on their walls. All of my work is done with pen plotting in mind. I'm using AxiDraw SE/A3 by Evil Mad Scientist and I love everything about this machine. Pen plotting is something that I want to write more about in the future. Blog # This year I neglected the blog a little. Mostly because I was focused on generative stuff, and I was doing that instead of writing posts. The pandemic didn't help either. I removed Google Analytics in favor of GoatCounter, a simple open source web analytics which are not tracking my readers. Even without writing much, I had more visits than in 2020. But you can see the drop in May, about the same time I removed Google Analytics. Coincidence or not, I can't say. The second drop happened in early December, as I moved posts under /blog prefix but screwed up the redirections. I can only hope search engines won't derank me too much because of that. People are still not sticking around after re

## Metaballs

DevFeed: [Metaballs](<https://devfeed.tech/articles/metaballs-37311.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/metaballs-generative-art/>)

Author: Stanko

Published: 2020-02-06T00:00:00Z

Content type: article

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [creative coding](<https://devfeed.tech/topics/creative-coding.md>), [Graphics](<https://devfeed.tech/topics/graphics.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [render](<https://devfeed.tech/topics/render.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [art](<https://devfeed.tech/tags/art.md>), [coding](<https://devfeed.tech/tags/coding.md>), [computer-graphics](<https://devfeed.tech/tags/computer-graphics.md>), [creative-coding](<https://devfeed.tech/tags/creative-coding.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [projects](<https://devfeed.tech/tags/projects.md>), [render](<https://devfeed.tech/tags/render.md>)

### AI overview

A project write-up about creating Metaballs, a generative art project that combines spheres into organic shapes, slices them, and renders their outlines as vector files. The author describes exploring metaballs, learning about marching cubes and marching squares, using an existing solution, and building tooling for immediate visual feedback.

### Source excerpt

I'm all about generative art these days. Today, I present you Metaballs, my latest creation. It is one of those projects that I visualized in my head and managed to pull it off exactly how I imagined it. Somehow I came up with an idea to generate spheres, smoothly merge them to get organic looking shapes, which then I would slice up and render the outlines.I ordered a pen plotter and that is the reason I'm focused on producing vector files. One of the final images looks like this (click on it to see more): Exploration # Not sure how I started thinking about slicing these blobby objects, but I had a clear vision of what I wanted to achieve. At this point I had no idea they are called metaballs. I asked on our company's #tech-creative-coding channel, if anyone is familiar with making something like this, and my colleagues pointed out the term metaballs and marching cubes algorithm. Definition # Wikipedia defines metaballs as: In computer graphics, metaballs are organic-looking n-dimensional isosurfaces, characterised by their ability to meld together when in close proximity to create single, contiguous objects. Which makes them perfect for what I had in mind - generating organic looking blobs. Implementation # The first try # Initially I wanted to implement it myself, but I didn't really know where to start. I had an idea to hack it by overlapping two spheres and calculate a curve between them. By rotating this curve, I would create a tube and merge everything together. It looks ok-ish for two spheres, but I wasn't completely satisfied. And it was impossible do it for more than two spheres. So I gave up early on this idea. Marching on # So I went back to the marching cubes algorithm. After some research I found a wonderful post, which very thoroughly explains implementation of marching squares.Marching squares are the same algorithm as marching cubes, but in 2D. Now I understood how algorithm works, but I gave up on implementing it myself. I was more interested in bei

## Neon, a glowy vector field

DevFeed: [Neon, a glowy vector field](<https://devfeed.tech/articles/neon-a-glowy-vector-field-37319.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/neon-generative-art-piece-made-using-2d-vector-field/>)

Author: Stanko

Published: 2020-01-22T00:00:00Z

Content type: article

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [Code](<https://devfeed.tech/topics/code.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [SVG](<https://devfeed.tech/topics/svg.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [core](<https://devfeed.tech/tags/core.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [project](<https://devfeed.tech/tags/project.md>), [svg](<https://devfeed.tech/tags/svg.md>)

### AI overview

The article explains Neon, an open-source generative art project that creates glowing lines from randomly generated vector fields. It describes how nearby vectors influence each successive point and how the resulting points are rendered as Bézier curves.

### Source excerpt

Recently I started playing with generative art. I'm new to the whole thing and I'm absolutely enjoying it. Today I want to show you the first generative art project I'm satisfied with. It is called Neon and you can check it out here or by clicking on the image below. I will try to explain in detail how Neon works, however this won't be a coding tutorial. But it is an open source project, and code is available here. My first attempts # These were very simple and I was just exploring various concepts and tools: Triangles Perlin noise grid Untitled Flow I'm sharing these to show that my initial work was pretty humble. The point is - don't be afraid to experiment with things like this. For me, it was easier than I thought it would be, and I enjoyed every minute of it. Vector fields # After watching Vladimir's talk about his Aesthetic Engine 2, I started experimenting with vector fields. This is an example of one randomly generated vector field: Think of it like it is an air or water flow. If this field was a river and you drop a leaf in it, these forces will take it and carry it around. If we plot the movement of the leaf, we'll get a line. If we draw a lot of these lines, we will visualize the flow of the field. That is the core concept I used with Neon. But for a start let's see how can we draw a single line. Drawing a line # To draw a line, we'll select a random point for its start (we are dropping a leaf). We need to define which vectors are applying "force" to our point. Let's use radial search radius of 1.5 times grid item size. We'll select only vectors that start in this area (nine in this specific scenario). For each one we will calculate a new force vector with the same direction, but with intensity reciprocal to its distance from the point. Meaning that the closer the vector is to the point, it will apply more force to it. Adding up all of these newly calculated force vectors will give us a single vector pointing where our next point should be. Let's draw the

## LOLWUT: a piece of art inside a database command

DevFeed: [LOLWUT: a piece of art inside a database command](<https://devfeed.tech/articles/lolwut-a-piece-of-art-inside-a-database-command-20614.md>)

Original publisher: [Read original article](<http://antirez.com/news/123>)

Author: Antirez

Published: 2018-09-12T15:20:28Z

Content type: opinion

Language: en

Sources: [Antirez](<https://devfeed.tech/sources/antirez.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [procedural art](<https://devfeed.tech/topics/procedural-art.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [art](<https://devfeed.tech/tags/art.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [code](<https://devfeed.tech/tags/code.md>), [command](<https://devfeed.tech/tags/command.md>), [computer](<https://devfeed.tech/tags/computer.md>), [database](<https://devfeed.tech/tags/database.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [generate](<https://devfeed.tech/tags/generate.md>), [hack](<https://devfeed.tech/tags/hack.md>), [hackers](<https://devfeed.tech/tags/hackers.md>), [hacking](<https://devfeed.tech/tags/hacking.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [perspective](<https://devfeed.tech/tags/perspective.md>), [process](<https://devfeed.tech/tags/process.md>), [randomness](<https://devfeed.tech/tags/randomness.md>), [redis](<https://devfeed.tech/tags/redis.md>), [replication](<https://devfeed.tech/tags/replication.md>), [technology](<https://devfeed.tech/tags/technology.md>), [useful](<https://devfeed.tech/tags/useful.md>)

### AI overview

Redis creator Salvatore Sanfilippo presents LOLWUT as a deliberately non-useful command with "hack value": an exploration of programming as craft and art, inspired by Georg Nees's generative work Schotter. LOLWUT renders a changing, parametric version of the artwork in a terminal using Braille characters, which provide a 2x8 pixel grid per character. The author describes the implementation as literate programming, intended to explain its choices like a tutorial. Starting with Redis 5, each major version is to bring a different LOLWUT, guided by three rules: it must do nothing technologically useful, run fast enough to be safe on production instances, and entertain. The command is framed as a reminder that programming can explore possibilities and serve human purposes beyond measurable technological results.

### Source excerpt

The last few days have been quite intense. One of the arguments, about the dispute related to replacing or not the words used in Redis replication with different ones, was the following: is it worthwhile to do work that does not produce any technological result? As I was changing the Redis source code to get rid of a specific word where possible, I started to think that whatever my idea was about the work I was doing, I'm the kind of person that enjoys writing code that has no measurable technological effects. Replacing words is just annoying, even if, even there, there were a few worthwhile technological challenges. But there is some other kind of code that I believe has a quality called "hack value". It may not solve any technological problem, yet it's worth to write. Sometimes because the process of writing the code is, itself, rewarding. Other times because very technically advanced ideas are used to solve a not useful problem. Sometimes code is just written for artistic reasons. In some way the Twitter discussion of the last days, mostly uninformed, chaotic, heated, made me think that, at this point, we are very far from the first hackers in the 60s. As I get older I find that it is harder and harder to talk about technology with an hacking perspective, where there are no walls or pre-cooked ideas, and the limit is the exploration. For everything you say there is a best practice. For every idea there is a taboo. To this new setup I say LOLWUT, since I don't feel represented by it, nor it represents hacking, at least in my vision. So the idea was to spend some technologically useless time in order to explore something of the 60s. My attention went immediately to one of the computer art pieces I love the most: Schotter, by Georg Nees (https://en.wikipedia.org/wiki/Georg_Nees). With the help of a plotter and ALGOL programs, Nees explored writing programs to generate art using caos (randomness) and repeating patterns. Schotter is remarkable because of the simplicit

## Animated line drawings with OpenCV

DevFeed: [Animated line drawings with OpenCV](<https://devfeed.tech/articles/animated-line-drawings-with-opencv-21653.md>)

Original publisher: [Read original article](<https://www.windytan.com/2017/12/animated-line-drawings-with-opencv.html>)

Author: Oona Räisänen (noreply@blogger.com)

Published: 2017-12-30T12:15:00Z

Content type: tutorial

Language: en

Sources: [Oona Räisänen](<https://devfeed.tech/sources/oona-raisanen.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [image effects](<https://devfeed.tech/topics/image-effects.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>)

Tags: [animations](<https://devfeed.tech/tags/animations.md>), [art](<https://devfeed.tech/tags/art.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [cmake](<https://devfeed.tech/tags/cmake.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [drawing](<https://devfeed.tech/tags/drawing.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [image](<https://devfeed.tech/tags/image.md>), [matrix](<https://devfeed.tech/tags/matrix.md>), [music](<https://devfeed.tech/tags/music.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [plotting](<https://devfeed.tech/tags/plotting.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

The excerpt shows how to use OpenCV's C++ drawing tools to create pixel-level animations and save them as video. A minimal CMake project links OpenCV, and a zero-initialized 1920x1080 `cv::Mat` provides a black canvas. The example builds animated concentric rings with rotating spokes; antialiased subpixel positions are represented by multiplying coordinates by 8 and using a three-bit shift. To give the graphics a vector-display glow, the author applies Gaussian blur, noting that convolution is CPU-intensive and that blur calculation consumed much of the rendering time. The excerpt ends mid-discussion, so it does not establish the full rendering or video-writing workflow.

### Source excerpt

OpenCV is a pretty versatile C++ computer vision library. Because I use it every day it has also become my go-to tool for creating simple animations at pixel level, for fun, and saving them as video files. This is not one of its core functions but happens to be possible using its GUI drawing tools. Below we'll take a look at some video art I wrote for a music project. It goes a bit further than just line drawings but the rest is pretty much just flavouring. As you'll see, creating images in OpenCV has a lot in common with how you would work with layers and filters in an image editor like GIMP or Photoshop. Setting it up It doesn't take a lot of boilerplate to initialize an OpenCV project. Here's my minimal CMakeLists.txt: cmake_minimum_required (VERSION 2.8) project (marmalade) find_package (OpenCV REQUIRED) add_executable (marmalade marmalade.cc) target_link_libraries (marmalade ${OpenCV_LIBS}) I also like to set compiler flags to enforce the C++11 standard, but this is not necessary. In the main .cc file I have: #include "opencv2/imgproc/imgproc.hpp" #include "opencv2/highgui/highgui.hpp" Now you can build the project by just typing cmake . && make in the terminal. Basic shapes First, we'll need an empty canvas. It will be a matrix (cv::Mat) with three unsigned char channels for RGB at Full HD resolution: const cv::Size video_size(1920, 1080); cv::Mat mat_frame = cv::Mat::zeros(video_size, CV_8UC3); This will also initialize everything to zero, i.e. black. Now we can draw our graphics! I had an initial idea of an endless cascade of concentric rings each rotating at a different speed. There might be color and brightness variations as well but otherwise it would stay static the whole time. You can't see a circle's rotation around its center, so we'll add some features to them as well, maybe some kind of bars or spokes. A simplified render method for a ring would look like this: void Ring::RenderTo(cv::Mat& mat_output) const { cv::circle(mat_output, 8 * center_, 8 *

## Doing the FizzleFade effect using a Feistel network

DevFeed: [Doing the FizzleFade effect using a Feistel network](<https://devfeed.tech/articles/doing-the-fizzlefade-effect-using-a-feistel-network-20604.md>)

Original publisher: [Read original article](<http://antirez.com/news/113>)

Author: Antirez

Published: 2017-08-29T14:35:14Z

Content type: article

Language: en

Sources: [Antirez](<https://devfeed.tech/sources/antirez.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [pixel](<https://devfeed.tech/topics/pixel.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>)

Tags: [cryptography](<https://devfeed.tech/tags/cryptography.md>), [effect](<https://devfeed.tech/tags/effect.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [game](<https://devfeed.tech/tags/game.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [linear](<https://devfeed.tech/tags/linear.md>), [network](<https://devfeed.tech/tags/network.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [pixels](<https://devfeed.tech/tags/pixels.md>), [random](<https://devfeed.tech/tags/random.md>), [red](<https://devfeed.tech/tags/red.md>), [replicate](<https://devfeed.tech/tags/replicate.md>), [resolutions](<https://devfeed.tech/tags/resolutions.md>), [screen](<https://devfeed.tech/tags/screen.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [transformation](<https://devfeed.tech/tags/transformation.md>)

### AI overview

The article uses a Feistel network to generate a random-looking, one-to-one sequence of pixel positions for a FizzleFade effect. Unlike repeated rand() coordinates, which may hit already-colored pixels and leave the last ones slow to appear, the mapping visits each position once. Its 16-bit example covers a 320x200 screen using 65,536 possible values, leaving some unused; for 1024x768, it proposes 20-bit input and output with 10-bit halves, requiring a changed frame stop condition. The JavaScript example uses eight rounds and a simple nonlinear function, chosen partly to make the distribution look random. The excerpt presents this as an alternative to finding suitable LFSR taps for different resolutions.

### Source excerpt

Today I read an interesting article about how the Wolfenstein 3D game implemented a fade effect using a Linear Feedback Shift Register. Every pixel of the screen is set red in a pseudo random way, till all the screen turns red (or other colors depending on the event happening in the game). The blog post describing the implementation is here and is a nice read: http://fabiensanglard.net/fizzlefade/index.php You may wonder why the original code used a LFSR or why I'm proposing a different approach, instead of the vanilla setPixel(rand(),rand()): doing this with a pseudo random generator, as noted in the blog post, is slow, but is also visually very unpleasant, since the more red pixels you have on the screen already, the less likely is that you hit a new yet-not-red pixel, so the final pixels take forever to turn red (I *bet* that many readers of this blog post tried it in the old times of the Spectum, C64, or later with QBASIC or GWBasic). In the final part of the blog post the author writes: "Because the effect works by plotting pixels individually, it was hard to replicate when developers tried to port the game to hardware accelerated GPU. None of the ports managed to replicate the fizzlefade except Wolf4SDL, which found a LFSR taps configuration to reach resolution higher than 320x200." While not rocket science, it was possibly hard for other resolutions to find a suitable LFSR. However regardless of the real complexity of finding an appropriate LFSR for other resolutions, the authors of the port could use another technique, called a Feistel Network, to get exactly the same result in a trivial way. What is a Feistel Network? === It's a building block typically used in cryptography: it creates a transformation between a sequence of bits and another sequence of bits, so that the transformation is always invertible, even if you use all the kind of non linear transformations inside the Feistel network. In practical terms the Feistel network can, for example, translate