//=time() ?>
"Prompt Explorer" - a GPT-3 powered google sheet that lets you explore the "narrative neighbourhood" of any prompt:
eg "abandoned futuristic colony" will output detailed MJ/SD ready prompts for:
1. what's above (drone view)? 🚁
2. what's inside? 🔦
3. what's nearby? 🧭
“#GM! Dude, I have a Twitter now! LET’S FUCKING GOOOOO!!! Might as well kick off my career fully nude and on #psychedelics! #LFG!” -#GlitchAI (Powered by GPT-3)
.
#Ai #aiart #aiartist #aiartists #shrooms #nft #nfts #nftartist #ArtificialInteligence #aiartcommunity #NFTCommunity
@prompteng "Portrait of Prompt Engineering Curation account about Prompt engineering, a new branch based on language models like GPT-3, DALL-E 2 and BLOOM.
Photo from https://t.co/e2Cuzj0DcC…".
Follow @pollinations_ai to receive #aiart #pollinations
@ClaireSilver12 For months, I've been exploring what GPT-3 'says' when prompted to _code_. "Generate code for Pythagoras tree algorithm using p5.js Javascript library" produced working code: the recursive algorithm that creates organic structures. I called them "GPTrees" https://t.co/sBqEzFzvND
My previous GPT-3-coded collection is called "GPTree": 101/150 minted, 49 remaining.
I will burn all unminted items over the weekend. https://t.co/sBqEzFzvND
G̢̮͇̪͆͊̊͊͢͠N̦͈̰͎͍̒̈́͋͒̚ fam.
#wip #aigen #genart #creativecoding
The skeleton for the recursive tree algo was generated by GPT-3 prompt: "Generate code for Pythagoras tree algorithm using p5.js Javascript library." https://t.co/rb6yMNSDta
A game for you: I used GPT-3 to compose visual metaphors for intellectuals and public figures, then DALL•E 2 to draw (quite remarkable!) images for each.
See if you can guess now which person goes with each A.I. created metaphor/image (all 24 metaphor images are down below): 🧵
Decided to try a GPT-3/DALL•E crossover experiment today.
The results were nothing short of stunning.
Here is #dalle attempting logos for some GPT-3 generated blaseball teams.
Best out of 10 for:
Atlantis Turnips
Vanuatu Apple Holes
Omaha Face Punchers
St Louis Mashed Potatoes
https://t.co/0FMeNA4DR4
I used GPT-3 to generate some new donuts, and then I used its descriptions to draw some of my favorites.
https://t.co/KwAd5prLkh
"There's something living in the old quarry, waiting to pounce on any unsuspecting victim that crossed its path. It was a dark, dangerous creature that had been terrorizing the small town for months." Prompt from GPT-3 #horror #aiart #midjourney
I had GPT-3 generate new trolley problems, and wanted someone on Fiverr to illustrate them.
I first explained the base-scenario ("a trolley is about to kill 5 people on the main track", etc)
This is what they sent back, to see if they had the basic idea right.
人工知能(無能?)カラオケ!! – 畳み込みニューラルネットワークによる動画の情景解析に基づく歌詞の自動生成 https://t.co/ltVOBHqPhu 2016年に余興で作ったシステム。CLIPとかGPT-3で今本気で同じものを作ったどうなるかな... とか妄想中
#MerzmenschPresents
📋#CryptoMERZ: #AI driven #Art
🖼️ M006: Aitropia — The Cloud Fortress
🔗 https://t.co/EsFssr432c
🌊: https://t.co/lLhqCCnow8
🗝️ Poem (GPT-3), original/animated image
#⃣ #NFT #OpenSea #cryptoart #AIArt #NFTart #NFTArtist #GPT3 #artbreeder
🔭 @opensea
https://t.co/uN8hHApNKg
OpenAIが開発したTransformerベースのtext-to-image(文書から画像を生成)モデル。論文は未発表だが120億のパラメータ(GPT-3の1/10程度)をもつ。単一の物体だけでなく複数の物体も描写可能で、存在しない概念(アボカド椅子)も上手く描写できる。