MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122183 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'ai-powered emoji generation system using text-to-image diffusion models.'
Inventor(s) include Dr. E. S. Madhan; Mr. Pillutlasam; Mr. Chilaka Devakreddy; and Mr. Nistala Venkatasai Pratheek.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a system for generating custom emoji-style images from natural language text prompts. The system includes a text preprocessing module configured to receive a natural language text prompt from a user and generate an enhanced text prompt using a large language model, an image generation module having a diffusion model fine-tuned on an emoji dataset that generates an emoji-style image based on the enhanced text prompt, and a user interface module configured to receive the natural language text prompt and provide the generated emoji-style image to the user. The large language model expands semantic content and contextual information to generate the enhanced text prompt. The diffusion model includes a Stable Diffusion model fine-tuned using Low-Rank Adaptation techniques. The system includes a post-processing module that applies background removal and resizes the emoji-style image to standard emoji dimensions."
Disclaimer: Curated by HT Syndication.
