Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MIDI-LLM: Adapting Large Language Models for Text-to-MIDI Music Generation

About

We present MIDI-LLM, an LLM for generating multitrack MIDI music from free-form text prompts. Our approach expands a text LLM's vocabulary to include MIDI tokens, and uses a two-stage training recipe to endow text-to-MIDI abilities. By preserving the original LLM's parameter structure, we can directly leverage the vLLM library for accelerated inference. Experiments show that MIDI-LLM achieves higher quality, better text control, and faster inference compared to the recent Text2midi model. Live demo at https://midi-llm-demo.vercel.app.

Shih-Lun Wu, Yoon Kim, Cheng-Zhi Anna Huang• 2025

Related benchmarks

TaskDatasetResultRank
Text-to-score generationCustom Text-to-Score prompt set 1.0 (test)
Valid File Generation Rate100
5
Text-to-score generation238 evaluation prompts
Prompt Adherence1.67
3
Showing 2 of 2 rows

Other info

Follow for update