This study developed and implemented a blended learning management (BLM) model integrating project-based learning (PjBL) and artificial intelligence (AI). The model was designed through a literature analysis and an expert evaluation using a focus group discussion. In November 2024, seven specialists assessed the model's usefulness, feasibility, appropriateness, and accuracy, and their evaluation indicated a high overall quality. Structured into five stages—project planning, practical development, AI integration, feedback loops, and final presentation—the model was implemented using 108 first-year undergraduate students enrolled in a Thai university Bachelor of Science in Information Technology program during the 2024 academic year to evaluate its effectiveness. Research instruments included a BLM plan, a multiple-choice academic achievement test, and a digital media creation skills assessment based on a scoring rubric. Data analysis was conducted using descriptive statistics and t-tests. The findings revealed that students' digital media creation skills after model learning significantly exceeded the predetermined criterion of 80% at the .01 level of statistical significance. Additionally, students demonstrated significantly higher academic achievement in digital media creation after using the model than before, also at the .01 level of statistical significance. This study presented a BLM that synergizes PjBL and AI to cultivate digital media competencies. Structured into five stages—project planning, practical development, AI integration, feedback loops, and final presentations—the model was validated through expert evaluation and empirical testing. These findings underscore the efficacy of blending hands-on, collaborative learning with AI-driven tools to meet contemporary educational demands.