AI summary: Meta has announced CM3Leon, an AI model that excels in text-to-image generation. Unlike most image generators that rely on diffusion, CM3Leon uses a transformer model, making it more efficient and faster. It also stands out for its ability to generate captions for images. The model was trained using a dataset of millions of licensed images from Shutterstock and uses a technique called supervised fine-tuning to improve performance. CM3Leon can generate detailed images from complex text prompts and edit existing images based on instructions.
Read more at TechCrunch…
