Suno v6 launches with all older models deprecated; heavy user finds it a big downgrade
Scobleizer · x · 2026-09-10
Suno v6 is out and all older models have been deprecated. User @tesseraantra, after rolling a few hundred generations, reports a mostly negative first impression:
- Works fine for songs intentionally written as songs, and follows prompted styles well; it no longer accepts empty style guides, generating a style from lyrics instead.
- Loses the old "Suno magic" of turning non-lyrical artifacts into songs.
- Noticeably worse at understanding lyrics and adapting music/composition to meaning.
- Positives: generation is very fast, and LLM-generated explicit directions may compensate for the audio model's weaknesses.
The author still thinks good songs will be made with v6, but mourns the loss of the older models' capabilities.
More from Multimodal
- LichtFeld Studio v0.5.4.3 adds community-built SteadySplats and voxelization features — janusch_patas · 2026-10-26
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26