You can expect model and code release from the @StabilityAI ecosystem to go exponential into 2023 as we get all the right systems and processes in place.
We are going as fast as we can and have made some mistakes on the way but are trying our best to truly democratize AI.
AI-generated character + a couple of hours of modelling.
AI saved me several days of work, with looking for references, sketches and coordination with a team.
We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts.
Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.
I remember when I got an early invite to try DALL-E 2 and I was frozen at the prompt text box for a minute and finally typed in "cat"😅. The art of prompts that the community has discovered and increasingly perfected over the last few months for text->image models is astonishing.
We've trained a neural net called Whisper that approaches human-level robustness and accuracy on English speech recognition. It performs well even on diverse accents and technical language. Whisper is open source for all to use. https://t.co/ueVywYPEkK
@gozmike@GergelyOrosz Yeah, this makes a ton of sense. 2020 and 2021 vintages could be rough, and GPs won't want to mark anything down until it's absolutely necessary.
@GergelyOrosz But you're right, serious risk associated with a company exiting below their last post money. With the potential of washing out a big chunk of common.