Meta introduces generative AI model CM3leon for text, image generation

Meta (formerly Facebook) has introduced a generative artificial intelligence (AI) model -- "CM3leon" (pronounced like chameleon), that does both text-to-image and image-to-text generation.

Published By: Shubham Verma | Published: Jul 15, 2023, 09:12 PM (IST)

Meta (formerly Facebook) has introduced a generative artificial intelligence (AI) model -- "CM3leon" (pronounced like chameleon), that does both text-to-image and image-to-text generation. Also Read: CBSE Cyber Attack: Claude AI under spotlight as IIT experts review CBSE's tech ecosystem

"CM3leon is the first multimodal model trained with a recipe adapted from text-only language models, including a large-scale retrieval-augmented pre-training stage and a second multitask supervised fine-tuning (SFT) stage," Meta said in a blog post on Friday. Also Read: Google launches Dreambeans: An AI app that turns your activity into personalised stories

With CM3leon's capabilities, the company said that the image generation tools can produce more coherent imagery that better follows the input prompts. According to Meta, CM3leon requires only five times the computing power and a smaller training dataset than previous transformer-based methods. Also Read: Intellemo AI Announces Quality-First Approach, Competing on Natural Human Expression, Voice Sync, and Cinematic Motion

When compared to the most widely used image generation benchmark (zero-shot MS-COCO), CM3Leon achieved an FID (Frechet Inception Distance) score of 4.88, establishing a new state-of-the-art in text-to-image generation and outperforming Google's text-to-image model, Parti.

Moreover, the tech giant said that CM3leon excels at a wide range of vision-language tasks, such as visual question answering and long-form captioning. CM3Leon's zero-shot performance compares favourably to larger models trained on larger datasets, despite training on a dataset of only three billion text tokens.

"With the goal of creating high-quality generative models, we believe CM3leon's strong performance across a variety of tasks is a step toward higher-fidelity image generation and understanding," Meta said.

"Models like CM3leon could ultimately help boost creativity and better applications in the metaverse. We look forward to exploring the boundaries of multimodal language models and releasing more models in the future," it added.

-- IANS

Get latest Tech and Auto news from Techlusive on our WhatsApp Channel, Facebook, X (Twitter), Instagram and YouTube.