No filming, all AI: Seedance 2.5 + Suno workflow creates lifelike Italian music video
azed_ai · x · 2026-11-06
Creator @shikoba86 released an experimental AI music video, "NON MI TROVI": an original Italian song with a fully synthetic performance—nothing was ever filmed.
The goal wasn't just pretty frames but a believable singer who could deliver a fast vocal, stay lip-synced, play the piano naturally, and remain consistent with the music across camera angles. Italian and a fast singing style were chosen deliberately to raise the difficulty of articulation, breathing and facial expression.
Production stack:
- Dreamina Seedance 2.5: reference-to-video, performance and lip-sync
- Magnific: character, location and visual references
- Suno: assisted production of the original song
- Topaz Labs: upscaling and refinement
- CapCut: editing, color grading and post-production
More from Multimodal
- Recreating GTA 6's Rockstar art style with Magnific + Nano Banana 2.1, prompt included — azed_ai · 2026-11-06
- No image or video models: developer generates visuals, music and SFX purely with Claude-written code — azed_ai · 2026-11-06
- ComfyUI: forcing full GPU offload for the diffusion model only — Rare_Subject2343 · 2026-11-06
- A Full CapCut PC AI Workflow for Making a Product Ad: Extend, Caption, Fix — JaynitMakwana · 2026-11-06
- One Breath: A Black-and-White Neon Journey Across 12 Cities at Night — Then-Creme9892 · 2026-11-06
- HeyGen's October drop: in-house voice model debuts #1 on Artificial Analysis leaderboard — HeyGen · 2026-11-06