Hartree

[Hartree @Hartree_Y]

@morymuch Are you coming to the party?

[UtterlyInteresting @UtterlyInterest]

If tea spread to your country by sea you call it tea, if it spread by land you call it chai. This is because the ports of Fujian and Taiwan use the coastal pronunciation "te", whereas Mandarin uses "chá"

[Exa @ExaAILabs]

https://t.co/NX99LxC7vL is now publicly available!

Metaphor is a search engine based on generative AI, the same sorts of techniques behind DALL-E 2 and GPT-3

1/

[Emm | scenario.com @emmanuel_2m]

Let’s keep using #StableDiffusion to design or create #game assets, quickly and consistently.

In 15 min, generated an army of golems with similar shapes and sizes, but various “materials” (lava, rock, water, ice, forest, sand, gold…).

No in-painting is needed. Thread 🧵

[852話(hakoniwa) @8co28]

「NovelAIっぽい絵」を「平面的なイラストっぽい絵」で出力する方法
同prompt同seedで実験
ネガティブプロンプトに「3d」を強調度合い変えて入れるだけです。
1枚目が何もなし
2枚目UC末尾に「3d」
3枚目UC末尾に「{{{3d}}}」
4枚目UC末尾に「{{{{{{3d}}}}}}」
AI 無編集
#NovelAIDiffusion #NovelAI

[Hartree @Hartree_Y]

@okashinausagis2 いいアイデアだね！職場でも今全般的デジタル化してる

[Hartree @Hartree_Y]

@okashinausagis2 そしていい音楽に私！

[Fermat's Library @fermatslibrary]

Tupper's self-referential formula is a formula that visually represents itself when graphed at a specific location in the (x, y) plane.

[Russ Maschmeyer @russ_maschmeyer]

AI unlocks unlimited product photography. 🤯

Recent advances have made it possible for merchants to turn mobile photos into high quality product images + ad creative.

AI can now learn and reproduce a product on demand. More…👇[1/10]

#ai #aiart #stablediffusion #dreambooth

[Silver Keskküla @keskkyla]

@hardmaru For color as well:

[AK @_akhaliq]

DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics

abs: https://t.co/O0fwSwnnDd
project page: https://t.co/bp5JaXNJ3x

[Christian Szegedy @ChrSzegedy]

AI alignment solved.

[Google DeepMind @GoogleDeepMind]

Today in @Nature: #AlphaTensor, an AI system for discovering novel, efficient, and exact algorithms for matrix multiplication - a building block of modern computations. AlphaTensor finds faster algorithms for many matrix sizes: https://t.co/E18DezRPTL & https://t.co/SvHgsa0SNV 1/

[Shane Gu @shaneguML]

GPU-accelerated sims (IsaacSim, Brax) + SoTA deep RL implementations will revolutionize deep RL research and app for control.

Also check out our Braxlines for Brax, including DIAYN, SMM etc that train on humanoids within minutes on free Google Colab TPU. https://t.co/KCb5jKXzDr

[ミチル @mitiruxxx]

#どこにもない作品あります
架空の雑貨

[Hartree @Hartree_Y]

@okashinausagis2 もうぅ、すごい惨事…

[Phillip Isola @phillip_isola]

Language-conditional models can act a bit like decision transformers, in that you can prompt them with a desired level of "reward".

E.g., want prettier #dalle creations? "Just ask" by adding "[very]^n beautiful":

n=0: "A beautiful painting of a mountain next to a waterfall."

[Hartree @Hartree_Y]

@okashinausagis2 原神思い出した～

[Squirrel with a Gun🔫🐿️🏳️‍⚧️Switch2/PC/PS5/XBX! @QuiteDan]

Squirrel commits an adorable 😊😘 robbery 🔫🐿
#indiedev #gamedev #UE5 #UnrealEngine5 #indiegame #blender3d #blender #b3d #indiegamedev #screenshotsaturday #wishlistwednesday

[Hartree @Hartree_Y]

@okashinausagis2 気にしすぎ！前者がいい！