Assessing artistic creativity has long been a challenge. Traditional tests are widely used but often require time-consuming manual scoring. Thus, researchers are exploring a new way, such as machine learning, for automated artistic creativity assessment. Recent research on visual artistic creativity assessment has demonstrated that machine learning methods are effective but constrained by their reliance on visual data alone. This study integrates textual descriptions alongside visual data for a more holistic assessment of paintings' creativity, which is more sophisticated to measure than simple sketches. The multimodal model was fine-tuned and leveraged both visual and textual inputs. It achieved approximately 95.3% accuracy in predicting the painting creativity scores, demonstrating a strong positive correlation (Pearson r = 0.96) with expert ratings. The study allows a text-image evaluation of paintings' creativity to better align with human interpretations.