🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

A very big moment today as we release our first video models - the team is on 🔥 Video is a whole new dimension for generative media and personally the one I have been more than excited about. The next few months working on these models is going to be completely epic. As always

The Old Man of Storr ⛰️🏴󠁧󠁢󠁳󠁣󠁴󠁿 - #StableVideo #stabilityai

Extending clips is now possible in ComfyUI with the Stable Video model. Need to find a way to introduce some noise or something, it's getting a little more and more overbaked as you extend the clips. 👇 Workflow below

Another HUGE release today with SDXL "Turbo"... our first real-time image generation model. This distilled version of XL generates image in 1 step!! IMHO we should have called it Ludicrous Mode.... next time!

Reinforcement learning explained x.com/i/status/17310…

We’re on stage at 9pm in Brighton tonight. Video projected to all four walls so we’ll actually get to see the whole show for once! London on Friday 🛸 feormfalorx.world/Tour-Dates

Introducing StableLM Zephyr 3B: A new addition to StableLM, bringing powerful LLM assistants to edge devices. This 3 billion parameter LLM, with a file size 60% smaller than 7B models, allows accurate, and responsive output on a variety of devices without requiring high-end

Amazing and mind-bending to see and hear the incredible Plaid in London last night with generative visuals from Emma Catnip - thank you for an epic night Andy Turner

Introducing Stable Zero123: Quality 3D object generation from single images. Stable Zero123, a new in-house generative AI model is capable of creating 3D objects from any input image. Due to improved training datasets and elevation conditioning, the model demonstrates 3D

Proud of the team today on releasing the Video API! Well done team Stability AI

thanks a ton Stability AI raising the absolute bar it has rotary embedding kernels digits in the tokenizer are split into individual ones bias terms removed and it retains the neox throughput optimizations i am going to push this thing to the absolute limits local gpt4?

Congrats to the Baseten team!

SD3 paper released today. Well done team!

Today, we’re excited to share an early preview of our latest video model @hotshotco. And it’s available for you to use today. Link to try + more results in the thread below 👇

The team at GibsonAI is working on generation of complete back-end systems, through to middleware and APIs. Doing some cool work.

Nailed it!!!

50% barrier beaten on ARC prize :)

MINIMAX IS UNHINGED → NAUGHTY PIKACHU This tool is too much fun. MIDJOURNEY PROMPT: flash photo, Batman and real life pikachu having fun at a house party, 1980s --ar 3:2 --stylize 75 --v 6.1 MINMAX PROMPT STRUCTURES: 01. The camera [motion/direction] as Pikachu and Batman

Gemini and Grok ended April with a ~10 million gap in store downloads, increasing to ~136 million by May.