-
Extends the 跳舞直播间 (dance room) system to one independent live room per character, with an operator playback-management/blacklist layer (T39), a "我的作品" page for paid users (T38), a standalone 人衣图生成 admin tool, and a new admin-dance-library.html page for curating the per-character dance clip pool with AI QC. On top of that, dance clips now have an explicit published (上架/下架) status: passing AI QC (or a manual admin override to "correct") auto- publishes a clip, failing it auto-unpublishes it, and only published clips are eligible for a room's random-fill pool — unreviewed/rejected clips stay in the library but no longer autoplay for viewers. Existing already-QC'd "correct" clips are backfilled to published on first boot so the room doesn't go quiet. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MvkJsRcQ2qEuaFea31rBY8
-
S1: person+garment images directly into ref2va with attribute_transfer produce correct face/outfit/motion in one call — no separate compose step needed. S2: reference_video_urls has a real, strong effect on output motion (A/B tested). S4: H3 Console's own POST /v1/assets endpoint (undocumented until now) solves asset reachability without exposing our own uploads/ publicly. Evidence and scripts in spike/s1-s2-s4-2026-09-02/. Propagated the one-step design into the requirements doc, MVCP design doc, the architecture doc, and H3-CONSOLE.md; dev-plan.md's spike section marked done and its task table updated accordingly.
-
Static video-gen testing tool (MiniMax native API, then fal.ai) that grew into an AI drama live channel backed by an internal H3 Console GPU cluster: shared virtual-playhead live playback, prompt submit/match/generate queue, admin CRUD for the video library, and bilingual (zh/en) semantic clip names. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>