Trumbone's Indigo 1.1 adds Scene DNA to keep AI video elements consistent
lmoroney · x · 2026-10-02
Trumbone shipped Indigo 1.1, an AI video tool whose headline feature Scene DNA reads your script, identifies recurring people, objects, and places, and builds a reference image for each — so shot forty's guitar matches shot two. It targets musicians making music videos, with new Photo Looks (24 treatments from one photo) and Property Tours features.
The takeaway for creators: decide which faces, props, and rooms must stay locked before generating the next clip — consistency only comes from what you deliberately hand the system.
More from Multimodal
- Suno confirms one-pass speech + background music generation that ducks and swells around the voice — suno · 2026-10-02
- Qwen-Image-2.1 tops open-weights image leaderboards, ranking #18 overall on T2I and editing — ArtificialAnlys · 2026-10-02
- Diffusion researcher Stefan Webb joins Inception as first DevRel engineer — volokuleshov · 2026-10-02
- stillwet: AI paints brushstroke-by-brushstroke in a simulated oil studio, channeling Friedrich — ctjlewis · 2026-10-02
- Ben Affleck fine-tunes open video models on own-shot data; Netflix bought his AI firm for $587M — rohanpaul_ai · 2026-10-02
- ComfyUI node pack adds LLM prompt enhancer for Qwen, MiniMax and Ideogram workflows — Constant-Tower9662 · 2026-10-02