Since the beginning of the twenty-first century, the rapid development of digital networking and intelligent technologies has led to a significant trend where images and videos are increasingly poised to replace the dominance of language and written text. An effective response to this new literary landscape is through media convergence, specifically the fusion of literary narratives with images and videos referred to as “the convergence of picture, literature, and text”. This concept encompasses the temporal and spatial interpenetration of linguistic and pictorial narratives, as well as the mimetic, metaphorical, and punning representation of reality achieved through the merging of text and imagery. It also highlights the symbiotic relationship between graphic, textual, and linguistic narrative structures. The narrative structures of contemporary Chinese text-image fusion have introduced new techniques, including traditional methods such as contrast and picaresque, alongside modern approaches like inversion and diagonal narratives. These techniques have become focal points in current literary creation and academic research, with the potential to develop a new theoretical discourse on media convergence that reflects distinct Chinese characteristics.