Discover and read the best of Twitter Threads about #dallemini
Most recents (9)
The most interesting and viral images you see produced by text-to-image models are not merely the results of the deep learning models themselves, but rather the result of a complex feedback loop between a human neural net🧠 interacting with an artificial neural net🤖.
🧵Thread👇
🧵Thread👇
You can clearly see this, because the prompts for images that end up going viral for one model, clearly don’t “work” for another model.
The best images are chosen from evolutionary selection at the community level, and each image are the result of human/model iterative feedback:
The best images are chosen from evolutionary selection at the community level, and each image are the result of human/model iterative feedback:
From the #dallemini phenomenon, it’s also clear that the most viral content is not related to particular art styles, or whether the model can produce high quality images (reflected in training data). But rather, whether the model can portray cultural items that people talk about.
TORIES ON DRUGS
An Ode
With (heavily curated) illustrative assistance from #dallemini
(Thread)
#ukpolitics #satire
An Ode
With (heavily curated) illustrative assistance from #dallemini
(Thread)
#ukpolitics #satire
Top of a poll of the Brits' figureheads,
All the while Winnie was popping the reds...
All the while Winnie was popping the reds...
And before he became the UK's top book-cooker,
Osborne was snapped snorting coke with a hooker...
Osborne was snapped snorting coke with a hooker...
"Putin fighting with monkeys for bananas" Art Gallery
#dallemini
inspired by @AsiaK1918
IMPRESSIONISM /1
#dallemini
inspired by @AsiaK1918
IMPRESSIONISM /1
SKETCH /2
EXPRESSIONISM /3
Ich hab darüber nachgedacht, was mich als aus bildwissenschaftlicher Sicht an #DallE 2 (und ebenso an #dallemini) interessiert. Es ist nicht die müßige Frage, ob das jetzt Kunst sei, sondern drei Aspekte, die mir bislang kaum diskutiert scheinen. Ein längerer Thread 1/21
Diese drei Aspekte wären, etwas kryptisch formuliert, 1. die spezifische Priorität der Sprache gegenüber dem Bild, 2. die Entkopplung von Stil und Ikonografie & 3. die Dominanz des Visuellen über das Optische. Was soll das heißen? 2/21
Erstens: Sprache und Bild. Text-to-Image-Generation basiert buchstäblich auf der Priorität der Sprache. Bildbeschreibungen werden zu magischen Kommandos, die scheinbar Bilder aus dem Nichts herbeirufen: Das Wort ward Bild. 3/21
You may have seen surreal and absurd AI-generated images like these ones...
These are all generated with an AI tool known as DALL·E mini
Let's talk about the history of #dallemini, and also *how* it works! ↓↓↓🧵
These are all generated with an AI tool known as DALL·E mini
Let's talk about the history of #dallemini, and also *how* it works! ↓↓↓🧵
First, let's clarify the different AI tools which many get confused about:
- DALL·E was an @OpenAI-developed AI project from Jan 2021
- DALL·E mini is a community-created project inspired by DALL·E
- DALL·E 2 is another @OpenAI-developed tool released in April (2/16)
- DALL·E was an @OpenAI-developed AI project from Jan 2021
- DALL·E mini is a community-created project inspired by DALL·E
- DALL·E 2 is another @OpenAI-developed tool released in April (2/16)
@OpenAI DALL·E mini was actually originally developed about a year ago, back in July 2021.
During a programming competition organized by @huggingface (an AI company), @borisdayma & some community folks (including myself!) developed a neural network inspired by DALL·E & studied it (3/16)
During a programming competition organized by @huggingface (an AI company), @borisdayma & some community folks (including myself!) developed a neural network inspired by DALL·E & studied it (3/16)
Tried to use #Imagen to generate collectable Japanese postage stamps about VR cats. I love these results!
“Ukiyo-e painting of a cat hacker wearing VR headsets, on a postage stamp” ❤️
“Ukiyo-e painting of a cat hacker wearing VR headsets, on a postage stamp” ❤️
Don’t worry, these VR cats are only slightly sentient 🙃
Sad Anakin Skywalker making sand castles: A serious and important study in art styles and media (submissions open)
1/ Cubist painting of sad Anakin Skywalker making sand castles
1/ Cubist painting of sad Anakin Skywalker making sand castles
2/ Close up pencil drawing of sad Anakin Skywalker making sand castles
3/ Neoclassicist painting of sad Anakin Skywalker making sand castles
Now that Twitter knows about #dallemini, y'all might as well have fun with these other free generative AI apps.
A few 💎's you might not know about...👇
A few 💎's you might not know about...👇
BoredHumans.com by @BoredhumansAI — huge collection of 50 artificial intelligence pages. Generators for AI Lyrics, @BoredApeYC PFPs, Joke Battles, Fake Academic Papers, etc.
artbreeder.com @Artbreeder by @StudioMorphogen & @_joelsimon
Quite literally breed images together to create... anything...
#Artbreeder
Quite literally breed images together to create... anything...
#Artbreeder
