Alberto Montiel @xaemax

Web Master albertomontiel.com Cabudare, Venezuela Joined October 2010

Tweets

187
Followers

52
Following

213
Likes

334

Alberto Montiel @xaemax

a year ago

@NASA If we can travel in time and we try to put "the seed of life" in the bigban event, we can defeat the dilema of random evolution and even ex nihilo creation? our creation will be a self creation, it's right? 🚀💫

0 1 1 14 0

View Details

Alberto Montiel @xaemax

2 weeks ago

El BigBang - Canción que dedica a stephen hawking por su aporte a la ciencia y a lo humano en general. Sígueme, comparte y disfruta! #albertomontielai #xaemax #podcast #musica #ciencia #stephenhawking #nasaenespañol #nasa #canciones #news #noticias #parati @NASA @NASA_es

0 0 0 27 0

View Details

Alberto Montiel @xaemax

a year ago

@NASA_es Si pudiéramos viajar en el tiempo y logramos "plantar la semilla de la vida" en el evento del bigbang, así como producir dicho evento, venceríamos el dilema de la aleatoriedad evolutiva de la vida así como el ex nihilo? sería un proceso de auto creación, es cierto? 🚀💫

0 0 0 25 0

View Details

Alberto Montiel @xaemax

2 years ago

@NASA_es Si pudiéramos viajar en el tiempo y lográramos llegar hasta el momento del big bang, podríamos colocar la semilla de la vida, ¿Sería un esquema válido y realista de "Auto creación humana"?

0 0 0 12 0

View Details

Alberto Montiel @xaemax

3 years ago

Y si casi las películas y series que vemos en tv e internet son generadas por inteligencia artificial? Sólo haría falta mandarlas desde un futuro no muy lejano. Como sea creo que es el futuro de estos medios... @DotCSV

0 0 0 20 0

View Details

LudovicCreator @LudovicCreator

3 years ago

🎨FUTURISTIC MINIMALISM V6🎨 Step by step you will see my prompting changing to adapt to V6. Here a first share trying to adapt my prompts. Base prompt : Visualize a [SUBJECT] in the style of Futuristic Minimalism, where advanced, sleek designs merge with the simplicity of minimalism. Picture this setting defined by clean lines, geometric shapes, and a mainly [COLOR 1] color scheme, accented with striking [COLOR 2] highlights. This scene combines the essence of the future with understated elegance, creating a space that is both highly functional and aesthetically captivating Inspired by @WorldEverett awesome work and prompts. Check ALTs for inspiration

10 30 169 8K 113

View Details

AK @_akhaliq

3 years ago

Tencent announces Paint3D Paint Anything 3D with Lighting-Less Texture Diffusion Models paper page: huggingface.co/papers/2312.13… Paint3D is a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs

3 119 564 72K 307

View Details

Brian Roemmele @BrianRoemmele

3 years ago

Meet Text To CAD. Create B-Rep CAD files and meshes from natural language prompts. Powered by the ML-ephant API from Zoo. Similar to my open source 3DPrintGPT. Link: text-to-cad.zoo.dev

58 232 1K 189K 829

View Details

Rowan Cheung @rowancheung

3 years ago

AI music generation just hit its inflection point. Microsoft Copilot can now turn text prompts into full music tracks. It's completely free & insanely good. Here's everything you need to know and a quick tutorial on how to create your own song:

92 348 2K 636K 3K

View Details

Alberto Montiel @xaemax

3 years ago

@javilop Haha 😂 genial. Genius 😎

0 0 1 133 0

View Details

Thibaud Zamora @thibaudz

3 years ago

It's a major breakthrough! Still very early but I can "image-prompt" clothes now. Need a bigger dataset and much longer training. For now, I have the global vibes of the clothes, the next step is to match it closer!

27 52 321 49K 184

View Details

El Club del Arte 🎨📷📚🖼🕍🎼 @Arteymas_

3 years ago

🐈

113 7K 27K 1.5M 1K

View Details

TechHalla @techhalla

3 years ago

👩‍🎤 Do you want to achieve consistency and total control when creating characters? 😎 It's now possible with ControlNet + FaceLock on RenderNet AI. I'll show you how to do it 👇 #AIArtCommunity #QuickGuide

18 47 275 49K 409

View Details

elvis @omarsar0

3 years ago

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!