1.5 moved rendering to clips but the Video stage only surfaced the scene script, so the workflow prompt field gave no hint of what an individual clip performs. Each clip now carries its description, shot size, and covered dialog lines into a brief panel above the composer, with a copy button feeding the prompt. The stage splits into player + a scrollable input inspector so the input stack can no longer squeeze the player out.
Changelogs
Dated notes for GitHub releases. Newest first.
- 2026-09-13 clip shot brief — per-clip brief in the Video composer; two-column Video stage (1.5.1)
- 2026-09-10 Build Scene + scene → clips — 3D blockout composer; vision/doc input; 1 scene : N shot clips; faithful scripts (1.5.0)
- 2026-09-07 chunking + cards — Story/script generate in chunks; ask_user cards appear (1.4.1)
- 2026-09-06 canvas merge — AI Canvas merges Agents + Playground; skills, memory, question cards (1.4.0)
- 2026-08-31 hardening — Prompt preview fails fast + never blocks Generate (1.3.2)
- 2026-08-31 patch — SvelteKit security bump so
npm audit fix --forceis never needed (1.3.1) - 2026-08-31 — Prompt review gate, ComfyUI error surfacing, saved scene setups (1.3.0)
- 2026-08-29 — Model per agent + clip-native export fps + video-extend continue (1.2.3)
- 2026-08-24 — Agent + Assets Management (1.2.1)
- 2026-08-23 — 1.2.0 / 1.2.1 video, H3, picker, release notes