Tags

Tag: audio-generation

• MiniMax Music 3 on the 780M: local text-to-song generation via ComfyUI 2026-08-19

  Running MiniMax Music 3, an 8B/0.6B hierarchical autoregressive music model, on a Radeon 780M through ComfyUI. INT8 quantization to fit shared VRAM, hand-wiring the real node graph behind a collapsed UI subgraph, and a ROCm context-poisoning flake caught mid-generation.