Mafe retweeted
THE WAY OF CODE, a project by @rickrubin in collaboration with Anthropic:
ALT Title cover for "The Way of Code: The Timeless Art of Vibe Coding" showing the title, subtitle, two interlocking circles, and credits "Based on Lao Tzu, Adapted by Rick Rubin"
ALT The first chapter's text with a flowing wireframe illustration by Claude on the left side.
ALT ASCII art rendering of Rick Rubin vibe coding with Claude.
Mafe retweeted
Introducing the Daylight Computer
It does less…
So you can be more 🍃
Order now: daylightcomputer.com
Mafe retweeted
Are you also attending @acm_chi and need a map to help you navigate the thousands of papers?
📣 I made a #chi2024 paper explorer for you!
Search by topic, drag to select regions and much more!
👉🏼 johnguerra.co/viz/chi2024Pap… 👈🏼
Mafe retweeted
We're sharing our learnings from a small-scale preview of Voice Engine, a model which uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker. openai.com/blog/navigating-t…
Mafe retweeted
To move this quickly, these companies figured out smart technical tricks that reduce computation with creative model architectures or use less data by applying industry-specific insights.
Watch the full episode— youtu.be/fmI_OciHV_8
Mafe retweeted
Lumiere is a space-time diffusion research model from Google Research. Using a single reference image, Lumiere can generate videos in the target style by utilizing fine-tuned text-to-image model weights.
Learn more about Lumiere → goo.gle/47WX6C2
Mafe retweeted
I had the privilege to talk to many amazing artists like @JonLamArt, @StevenZapata @FlippedNormals @patrickbrownart and scientist like @ravenben about the harmful effects of current popular Generative AI models:
Watch full video: youtu.be/ZJ59g4PV1AE?si=SzqJ…
Mafe retweeted
Together with @AndrewYNg and the DeepLearning.AI team, we're excited to launch this new, free course taught by @asangani7. More in the announcement below ⬇️
Prompt Engineering with Llama 2, a short course built with @AIatMeta, is live! 📣
Learn prompting best practices, advanced techniques, how to use Code Llama as a pair programmer, and how to implement safe AI practices, all in one course!
Join now: hubs.la/Q02mwKDS0
Mafe retweeted
Happy to announce our partnership with @morphaistudio, leveraging Stability AI’s model to revolutionize visual storytelling in generative AI video 🫶
You can join the waitlist here to try it out: morphstudio.com
Morph x @StabilityAI ! A groundbreaking collaboration bringing you the next-gen AI video creation workflow. Just let your ideas flow in, and watch as vivid videos come out.
With Morph Studio's All-in-One video generation solution, your inspirations from text, images, or existing videos evolve into captivating stories. Experience seamless creation with multi-parallel connections for every spark of creativity. Dive into the AI era with us, where every idea finds its vision.
Join the waitlist here: morphstudio.com
Mafe retweeted
🔥Playground v2.5 is here: our newest foundation model creates images with more vibrant colors, across many aspect ratios, and even more ways to bring your imagination to life.
Give it a try for free and see what others are making on Playground.com.
Mafe retweeted
Announcing Stable Diffusion 3, our most capable text-to-image model, utilizing a diffusion transformer architecture for greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
Today, we are opening the waitlist for early preview. This phase is crucial for gathering insights to improve its performance and safety ahead of open release.
You can sign up to join the waitlist and learn more here: bit.ly/3OR2qQF #stablediffusion3
Prompt: Epic anime artwork of a wizard atop a mountain at night casting a cosmic spell into the dark sky that says "Stable Diffusion 3" made out of colorful energy
Mafe retweeted
Introducing Gemma: a family of lightweight, state-of-the-art open models for developers and researchers to build with AI. 🌐
We’re also releasing tools to support innovation and collaboration - as well as to guide responsible use.
Get started now. → dpmd.ai/3UJu1Y1
ALT The word “Gemma” and a spark icon with blueprint styling appears in a blue gradient against a black background.
Mafe retweeted
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.
openai.com/sora
Prompt: “Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes.”
Mafe retweeted
Today we're introducing Gemini 1.5, our next-generation AI model. It shows dramatically enhanced performance, including long-context understanding across modalities, which opens up new possibilities for people to create and build with AI → goo.gle/4bEXIPL #GeminiAI
ALT Gemini logo, which is a blue ombre diamond sits above the text that reads “Introducing Gemini 1.5” on a black background.
Mafe retweeted
Stable Cascade is now available in research preview for non-commercial use. This innovative text to image model introduces a three-stage approach, featuring enhancements for fine-tuning and training efficiency with a focus on further eliminating hardware barriers.
Learn more here: bit.ly/4bC52Mg
Mafe retweeted
Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed.
MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️ bit.ly/42HkpyN
Mafe retweeted
Excited for all that people will achieve with this next generation of AI, as we bring the power of Copilot to anyone, anywhere, on any device.
This quoted post is unavailable.
Mafe retweeted
Unleash your creativity using Imagen 2: Google DeepMind’s most advanced text-to-image technology. 🎨
Try it now on Bard, @Google's latest AI experiment ImageFX and Search Generative Experience (SGE). → dpmd.ai/google-imagen-2