Yue2 releases AudioEncoder model, enabling Audio2Audio workflows like image-to-image
TomLikesRobots · x · 2026-09-13
Yue2 has released an AudioEncoder model alongside its standard generation model, converting audio into latent data so users can do "Audio2Audio" transforms. A creator tested it by regenerating an earlier MV track: overall vibe preserved, with new nuances and vocal timbre — an interesting arrangement tool. Note: omitting lyrics yields English-like gibberish instead of Japanese. The quoted post is an AI-generated MV combining Qwen3.8-27B for lyrics, AceStep1.5XL for music, Krea2 for characters, and MinimaxH3 Ref2V for video.
More from Multimodal
- Element Forge: open-source editable AI VFX for real footage in ComfyUI — zitroffell · 2026-10-30
- Claymation body horror on 8GB: three wrong settings, not the GPU, made local renders slow — roro9- · 2026-10-30
- AI-generated Haribo Starmix bean bag product shot looks like a real catalog page — Delahuntagram · 2026-10-30
- MiniMax LoRA creator ships open-source ComfyUI alternative to Higgsfield's Influencer Studio — infroy28 · 2026-10-30
- Scenario open-sources 3D OS: 80 agent skills taking sketches to game-ready assets — Scobleizer · 2026-10-30
- Open-source ComfyUI app reshoots footage keeping camera and framing, swapping scenes — 3dkvisual · 2026-10-30