This paper explores the integration of Large Language Models (LLMs) into process modeling to enhance accessibility and efficiency. Traditional process modeling methods are often time-consuming and require extensive expertise, making them challenging for non-experts. The authors propose a framework that leverages LLMs to automatically generate and refine process models from textual descriptions. The framework includes innovative prompting strategies, a secure model generation protocol, and an error-handling mechanism. A concrete system is implemented, using the Partially Ordered Workflow Language (POWL) for intermediate process representation, which ensures soundness and supports exporting models in standard notations like BPMN and Petri nets. Preliminary results demonstrate the framework's ability to streamline process modeling tasks, highlighting the transformative potential of generative AI in Business Process Management (BPM). The evaluation compares the framework's performance with state-of-the-art LLMs, showing that GPT-4 outperforms Gemini in generating accurate and optimized process models. The paper also discusses limitations and future directions, including expanding process perspectives, extended evaluation, direct BPMN generation, and enhanced interactivity.This paper explores the integration of Large Language Models (LLMs) into process modeling to enhance accessibility and efficiency. Traditional process modeling methods are often time-consuming and require extensive expertise, making them challenging for non-experts. The authors propose a framework that leverages LLMs to automatically generate and refine process models from textual descriptions. The framework includes innovative prompting strategies, a secure model generation protocol, and an error-handling mechanism. A concrete system is implemented, using the Partially Ordered Workflow Language (POWL) for intermediate process representation, which ensures soundness and supports exporting models in standard notations like BPMN and Petri nets. Preliminary results demonstrate the framework's ability to streamline process modeling tasks, highlighting the transformative potential of generative AI in Business Process Management (BPM). The evaluation compares the framework's performance with state-of-the-art LLMs, showing that GPT-4 outperforms Gemini in generating accurate and optimized process models. The paper also discusses limitations and future directions, including expanding process perspectives, extended evaluation, direct BPMN generation, and enhanced interactivity.