(1/3) Today, we're publishing our research paper that dives into the underlying technology powering Stable Diffusion 3.
Prompt: A beautiful painting of flowing colors and styles forming the words “The SD3 research paper is here!”, the background is speckled with drops and splashes of paint.
🚨 New model dropped from @StabilityAI
It is now available in early preview #StableDiffusion 3!
This model uses the diffusion transformer architecture, the same used by #Sora
It has greatly improved performance in multi-subject prompts, image quality, and spelling abilities
@Google released a family of open source model called #Gemma
They are built with the same technology used for #Gemini
Two version available: Gemma 2b and Gemma 7b
The 7b version beat mistral 7b and LLama 2
🚨 Google released the version 1.5 of #Gemini Pro
It have up to 1 MILLION context length 🤯
Can process 1 hour video long, 30K+ lines of code and 700K+ words!
🚨 New model dropped by @StabilityAI
Stable Cascade is a new text to image model building upon the Würstchen architecture.
It is made of three different models called stages that allows for a hierarchical compression of images.
Stable Cascade performs best in both prompt alignment and aesthetic quality in almost all model comparisons.
Goodbye Goole Bard, Welcome Google #Gemini
It is now available also Gemini Ultra 1.0 with a monthly subscription of Gemini Advanced, starting from €21.99 / month
We’re bringing Gemini directly to your phone with a new app on Android and in the Google app on iOS. 🤝
Ask Gemini to generate custom images for a party invite, for instructions on changing a flat tire, and much more. → https://t.co/EfD6YDn6oK