Pansori is a traditional Korean narrative musical form that combines sung passages with spoken narration (aniri) under explicit rhythmic cycles (jangdan). While recent text to-music models achieve strong results on mainstream genres, their behavior on underrepresented traditions remains largely unexplored. We adapt ACE-Step to pansori via LoRA-based fine-tuning and compare its adaptation to Korean pop as a mainstream baseline. We evaluate our results through quantitative analysis with Fréchet Audio Distance (FAD) and qualitative assessment by an expert pansori per former. Our study highlights challenges and partial successes in adapting to pansori. Future work will extend text-to-music models toward cultural diversity and traditional music.