A Dalle-3 and GPT4-Vision feedback loop
Start with a text prompt, let DALLE-3 generate an image, then GPT-4 Vision turns that image back into a text prompt, DALLE-3 creates another image, and so on.
Here are some crazy examples.
- Start with a sailboat but bias GPT4V to “replace everything with cats”: https://dalle.party/?party=0uKfJjQn
- A regular sized goat on a wild rampage through a terrified and burning city. The goats insane energy is flinging pedestrians and cars aside as it rockets through the scene of a crowded city Street with overwhelming power: https://dalle.party/?party=vCwYT8Em
Technology Connections Alec tries to get LED Christmas lights to look more like incandescent ones
A truly noble goal.
A day passing on planet Earth seen from 36,000 kilometers by the satellite Himawari-8
drawfast.tldraw.com
Real-time editing of a Stable Diffusion image guided by a prompt and your sketch.
What to do after falling into water with clothes on
The jeans trick is so good.
DeArrow
DeArrow is an open source browser extension for crowdsourcing better titles and thumbnails on YouTube. The goal is to make titles accurate and reduce sensationalism. No more arrows, ridiculous faces, and no more clickbait.
Opening a can of mixed nuts in space
They’re just in there partying until they’re eaten.
A dolphin reacts to Mariah Carey’s whistle note
Perfect pitch puzzle
Wordle for melodies. Kinda.