MIDI-LLM: Adapting Large Language Models for Text-to-MIDI Music Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909889558740992 |
|---|---|
| author | Wu, Shih-Lun Kim, Yoon Huang, Cheng-Zhi Anna |
| author_facet | Wu, Shih-Lun Kim, Yoon Huang, Cheng-Zhi Anna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIDI-LLM: Adapting Large Language Models for Text-to-MIDI Music Generation Wu, Shih-Lun Kim, Yoon Huang, Cheng-Zhi Anna Sound Computation and Language Multimedia 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. |
| title | MIDI-LLM: Adapting Large Language Models for Text-to-MIDI Music Generation |
| topic | Sound Computation and Language Multimedia |
| url | https://arxiv.org/abs/2511.03942 |