Discover and read the best of Twitter Threads about #generativeart

Most recents (24)

1/n I made a list of the 13 most mind-bending Stable Diffusion uses I’ve seen so far. 🌈
See🧵for details.

#stablediffusion
2/n Architectural Sketches
@rostenbach created incredible architectural renderings which made me think of future architecture generated by ai
artstation.com/blogs/rostenba…
3/n Search Engine
@sharifshameem scrapped millions of SD-generated images and turned them into a @LexicaArt search engine for creative assets
Read 20 tweets
🤯 You can now “remix” your txt2img AI prompts!

One of the biggest issues with AI generated images relies on the artists’ workflow and the controls they can have over their creation. Every new prompt usually creates a unique piece of art, thus making it hard to tweak the result.
But now with this new update by Midjourney, we can finally regain some level of control in the process.

I can’t wait to see what people create with it. On my side, it’s a blessing as I work on my collections and try to maintain consistency across my different pieces.
Thanks @midjourney for this new feature. Hopefully many more to come in that same vein. What would you do with it?

Follow me to stay informed & inspired:
linktr.ee/manu.vision

.

#aiart #generatedart #aigeneratedart #generativeart #genart #midjourney #midjourneyremix
Read 3 tweets
How do we express people's emotions about Tomorrowland through generative music?

Which musical aspects are self-produced and which ones are randomly generated by the algorithm?

How do happiness, anger, fear, and sadness sound in Pillars of Tomorrow?

All the answers below👇🧵🎶
In this generative piece, there are 4 instruments: bass, piano, percussion (hi-hat, kick, snare, claps, fx sounds), and a quiet pad.

All the rhythms are self-written using Ableton, exported, and randomly selected to create the backbone of our generative music NFT.
This approach was chosen because generative harmony is more euphonic compared to generative rhythm.

It's easier to control how something sounds(generative harmony) compared to adding randomness to when sounds are triggered(generative rhythm).
Read 14 tweets
Have you seen #videoart on @fx_hash_ before?

Teleport Loopr is my genesis💫

Mints open in 10 hours!⏳
[ Sept 14th / 15:00 UTC ]

Follow this thread ! 🧵#fxhash
#creativecoding #p5js #generativeart #CleanNFT
Videos per iteration:

[3], [4] or [5]

Color inversion effect may be applied to:

[ one video ], [ none (rare) ] or [ variable (super rare) ]
Read 8 tweets
Diffusion models is the new trend and everyday new enthusiasts approach these tools to make art and create awesome applications.
There is a ton of beautiful pictures made with #generativeart but have you ever tried and failed?
Me, many times😁
A thread to improve your prompts⬇️
1. Sometimes less is more. Writing hundreds of characters is not the right way to produce beautiful images. Consider that there are "classes" like 4k or high-resolution which embeds a lot of characteristics.
These are already available in @StableDiffusion or #discoart @JinaAI_
2. More detailed, more precised. If you use a specific jargon to obtain a certain style or effect, it is quite sure that you will be impressed from the result!
Try something very specific using technicalities like
infrared photo or sticker illustration, also tattoo works!
Read 5 tweets
Have you seen #videoart on @fx_hash_ before?

Teleport Looper is my genesis💫

Mint opens:
Sept 13th / 15:50 UTC

Follow this thread ! 🧵#fxhash #tezos
#creativecoding #p5js #generativeart #CleanNFT
Link:

fxhash.xyz/generative/192…

There are 30 .mp4 files available to be randomly chosen by the code ~

~ videos per iteration:

[3], [4] or [5]

~ color inversion effect may be applied to:

[ one video ], [ none (rare) ] or [ variable (super rare) ]
All videos are part of my audiovisual research and were recorded from 2016 to 2021 in Brasil, Chile and Canary Islands ~

They're all short and looped in Teleport Looper project, just like moving photos:
Read 6 tweets
I've been #creativecoding #videoart for 5 years in python (check my vimeo) and now that I transposed my codes to #p5js, I feel like I found my NFT place on @fx_hash_

This is my genesis and will be droped sept 11th

More info and iteration tests bellow!🧵
#generativeart #fxhash
There are 30 videos available to be randomly chosen by the code. Each iteration creates a loop with:

3, 4 or 5 videos

A chance of inverting colors in one of them

A small chance of applying the invertion to a variable video each loop
All videos take part on my audiovisual research and were recorded from 2016 to 2021 in Brasil, Chile and Canary Islands

They're all short and looped in this project, just like moving photos💫
Read 4 tweets
Love the X/Y Plot feature in AUTOMATIC1111's #stablediffusion WebUI. Once I have an image I like, I can do a quick search of the latent space around it across different settings. 1/3 #aiart #ai #aiArtist #MachineLearning #deeplearning #aiartcommunity
Link to AUTOMATIC1111's WebUI Repo here. Still have to check out its inpainting/outpainting implementations plus a few other features. 3/3 #stablediffusion #aiart #aiartists #ai #aiArtist #MachineLearning #deeplearning #aiartcommunity github.com/AUTOMATIC1111/…
Read 3 tweets
We’re at the frontier in web3, digital arts, & NFTs!

How are you keeping up?

Here's a cream-of-the-crop, monster 🧵 of key resources for both newbies & OGs...

(1/25)
“My journey through NFTs & Web3 has been as much of an education in Technology, as it has been in Philosophy, Economics, Marketing, Management and Entrepreneurship. Did you get that MBA too?”

- @WhaleShark_Pro

(2/25)
Let’s make this a world-class resource for new builders, creators, dreamers.

If I've missed them - add a key resource in the comments✍️

(3/25)
Read 33 tweets
Let’s talk about the texture of Running Moon today. Texture development is undoubtedly the most exciting and challenging part of the dev process that took most of my time. It is also an element that has shifted dramatically over the months.
1/
#generativeart #artblocks
Running Moon was initially influenced by my plotter practice: It was rendered in SVG and had a very precise feeling. There were lines and subtle gradients. I think outputs at this stage would produce exciting plotter paintings, but as standalone pieces, they need more.
2/
When robots physically render my work, they add additional layers of surprises. I hope to find that element of surprise in Running Moon. Therefore, I started experimenting with techniques that were beyond my comfort zone and ended up with many “failed’ experiments.
3/
Read 6 tweets
Today I want to share more about the color palettes of Running Moon. Running Moon has a collection of 36 color palettes. Each palette contains 6 seed colors. The final painting uses variations generated from these 6 colors.

"Whisper" showing here.
1/
#generativeart #artblocks
Why 6? My plotter painting practice influences it. In my plotter watercolor practice, I found 6 to be my stable choice because 6 colors can produce a diverse range of variations with some mixing, but going above 6 could lead to some dull colors for me.
2/
I started Running Moon with a much smaller set of color palettes, primarily in the yellow-blue range; here are some early outputs. Although I originally planned to keep Running Moon close to this range, I decided to try some other combinations for fun...
3/
Read 7 tweets
it's time to talk about my side project:

👉🏻 Introducing Prompt Press (prompt.press) - AI generated artwork inspired by current events.

#aiart #generativeart #aiartcommunity #AiArtwork
Over the past few months I've found myself absolutely fascinated with #AIart or #generativeart - whatever you want to call it.

You may have heard of #dalle2, #imagen or #parti. These are all amazing models (with limited access) that generate images of whatever you can describe.
"whatever you describe", the prompt, is key to navigating latent space and generating an interesting image.

This is such a skill, there's a whole field emerging called Prompt Engineering.
Read 9 tweets
YOU are going to make a piece of generative art right now in 10 minutes.

No watching tutorials, no downloading software. Just your browser and 21 lines of code.

By the end you’ll have a basic, but fun abstract generative art collection like this.

#generativeart
Before I start, I want to note that this approach builds upon a thread by @abwagmi that got me started in the space and I made sure he was ok with me doing a similar thread.
Altho i’ve been a fan of generative art for years, I only started making it 3 months ago. The question I hear over and over is “how do I start?”

It took me years and dozens of false starts before one thread finally pushed me over the edge. So I want to do the same here for you
Read 23 tweets
Color is probably the trickiest thing to master, especially using code. I wrote a thread breaking down color models and how to manipulate color in @p5xjs 🧵 1/n Image
There are several color models out there, you're probably already familiar with RGB - Red, Green, Blue. Each color is represented by three values ranging between 0 - 255 (256 Possibilities). Image
The problem with RGB is that it is meant to be machine-readable, your brain doesn't intuitively know why 212,24,118 is the color it is. It's meant to control the pixels on the screen and doesn't translate well to other uses, especially in making art.
Read 12 tweets
I'm contributing to an ongoing diffusion artist studies project 🎨started by @proximasan and @sureailabs

All images were made with Disco Diffusion 4.1 by @Somnai_dreams

Expect updates in the thread! 👇

#AIArt #aiartcommunity #generativeart #MachineLearning
Tyler Edlin
RHADS
Peter Mohrbacher
Felix Kelly

Basic settings + Vitl14 activated.
Read 13 tweets
Coding #generativeArt can be frustrating! Computers are extremely literal, and never know what you "meant".

Here are some things you can do to get help with problems you're having with your art.
1. Pause, breathe, and read the error.

If you run into a problem and immediately ask someone for help, you won't learn as much as solving it yourself. And if you solve your own problem, you won't have to wait for someone else. So see if you fix your own issue.
If you got an error message, read it!

Maybe it says you can't divide by zero, or that a file isn't found?

You might be given a line number, told what function errored, or hinted what data is invalid. Then, you can fix the problem without even needing to ask anyone.
Read 11 tweets
Para el turno de tarde...

"Desalmados" será, si la campaña en Verkami termina con éxito, la primera antología de microrrelatos e ilustraciones creados por inteligencia artificial. ¿Queréis saber de qué va esto? Dentro vídeo 👇👀
¿Queréis algunos ejemplos de lo que se podrá encontrar?
Dentro imágenes perturbadoras 👀👇 ImageImage
Dejo aquí el enlace a Verkami, pero seguid leyendo el hilo para más datos y curiosidades 👇
verkami.com/projects/31989…
Read 42 tweets
This weekend I played with 3 things I ♥: machine learning, #generativeart, and the web.

Here's a small neural network running entirely in a #webgl GLSL shader that hallucinates thousands of new handwritten digits in real-time.

How so? 👇🧵
I first learned about CPPNs in "Generating Large Images from Latent Vectors" by @hardmaru back in 2016 (!).

At the time, GANs were stuck at 256px and I was amazed to learn about these fast, high resolution, generators.

blog.otoro.net/2016/04/01/gen…
The fact that they operate on pixel coordinates makes them particularly good candidates for GLSL shaders.

(figure by @hardmaru)
Read 12 tweets
Hex by @yiwen_lin

Tech 🧑‍💻: using math (lots of math), to create hexagons and to fill them with lines of various properties

Looks 🎨: love that even if some hexagons overlap they still look good, even add to the overall depth of the generated piece

Löv by @JuhaniHalkomaki

Tech 🧑‍💻: branch and leaves generation, with p5js

Looks 🎨: the various shapes of the leaves, the colours, how the branches interact with the white box 'wall', it's all VERY beautiful

Read 7 tweets
The whole "Window" collection is now minted out. Here's a bit of background process.

First off, I gave myself the constraint of only using the Canvas API. No WebGL, shader or image texture. @nodes_io was the perfect companion to bring it from prototype to final state.

1/7
👇
The whole graph is pretty succinct so let's see how it is structured.

2/7 Image
A "Portal" logic is used to reduce #blueprintsfromhell spaghetti: it allows me to send data from 1 point of the graph to N others without dragging lines all over. Here, it sends the config computed from @fx_hash_ features to the nodes taking care of geometry and drawing.

3/7 Image
Read 7 tweets
Unbuilt by @jMarkusiewicz

Tech 🧑‍💻: applying sacral architectural rules in code

Looks 🎨: excellent colour choice and doesn't look like a generative output! the name and date underneath the generated layout is a nice touch

Indirection ⤳⤖⇶ by @notlion

Tech 🧑‍💻: using fonts (Unicode Arrows) with algorithms

Looks 🎨: the way the art unfolds and generates the paths makes it really interesting, a nice touch is that few of the arrows are in a different/highlight colour

Read 7 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!