Meta is dominating AI!
Meta AI, has recently revealed its new generative model for text and images called CM3leon. CM3leon is a multimodal foundation model that can generate images based on text input, as well as captions based on image input. CM3leon is the first multimodal model trained with a recipe adapted from text-only language models, which makes it more efficient and versatile than previous methods. CM3leon also achieves state-of-the-art performance for text-to-image generation, outperforming Google’s Parti model. CM3leon is currently a research effort and it is not clear when it will be available to the public.
Credit MattVid Pro