{"id":432,"date":"2026-09-10T22:15:10","date_gmt":"2026-09-10T13:15:10","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/10\/yue2-3b-music-generation-model\/"},"modified":"2026-11-03T16:08:24","modified_gmt":"2026-11-03T07:08:24","slug":"yue2-3b-music-generation-model","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/10\/yue2-3b-music-generation-model\/","title":{"rendered":"YuE2-3B Music Generation Model for Lyrics and Style: 12GB+ VRAM"},"content":{"rendered":"

Sample outputs are available on the model card<\/a>.<\/em><\/p>\n

<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\nm-a-p\/YuE2-3B<\/a><\/td>\n<\/tr>\n
Family guide<\/td>\nYuE2 guide (3 articles)<\/a><\/td>\n<\/tr>\n
Publisher guide<\/td>\nM-A-P: models and licenses<\/a><\/td>\n<\/tr>\n
Published<\/td>\n2026-09-10<\/td>\n<\/tr>\n
License<\/td>\ncc-by-nc-4.0<\/td>\n<\/tr>\n
Formats<\/td>\nsafetensors<\/a><\/td>\n<\/tr>\n
Paper<\/td>\narXiv:2503.08638<\/a><\/td>\n<\/tr>\n
Source type<\/td>\nPrimary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Values determined by this site’s code when the information was collected. Dates are JST.<\/em><\/p>\n

<\/p>\n

Overview<\/h2>\n

m-a-p has released “YuE2-3B”, an open music generation model that generates complete songs with vocals and accompaniment from lyrics and style prompts. It adopts a mechanism where an AR-NAR Mixture-of-Transformers backbone describes scores and semantic tokens, acoustic latent representations are generated via flow matching, and a VAE converts them into stereo audio.<\/p>\n

Specifications<\/h2>\n