Tech giant Meta has developed AI technology that creates high-quality images from written prompts, entering a field gaining momentum with tools like Dall-E, Midjourney, and Adobe Firefly.
Meta, which recently launched Twitter rival Threads, has unveiled its latest project, CM3Leon. The AI technology generates images from text descriptions and vice versa, producing coherent imagery with remarkable detail.
Meta demonstrated CM3Leon’s abilities by sharing images created from prompts such as a small cactus wearing a straw hat and neon sunglasses in the Sahara desert.
Users can refine the image quality by making simple adjustments. For example, adding sunglasses, face paint, or achieving a vintage look for portraits.
Although image-generation models are advancing, Meta has not provided a timetable for CM3Leon’s availability.
Meta has been active in AI, unveiling the LLaMA model for academic researchers, the Voicebox studio for speech synthesis, and the MusicGen tool for generating music from text description. – AFP Relaxnews
Credit: The Star : News Feed