wind-comic

ChrisChen667788/wind-comic is ranked 6,418 among these 8 peers; FireBird-Technologies/Auto-Analyst is ranked 6,419.

Multi-agent AI studio · reusable characters · novel→season splitting · director's control room · real-time collab · bring-your-own LLM. Most "AI video" tools give you a 5-second clip from a one-line prompt. It works because it doesn't try to be one giant model. It's an **honest multi-agent pipeline** where each role (Writer, Director, Producer, Character Designer, Storyboard Artist, Cameo Locker, Lipsync, Editor) is a specialist that hands off with strict consistency contracts. Plus a **real-time multiplayer

timeline** to edit with your team like Figma for film. The **Director** threads control across the seven pipeline agents (eight roles including the Director); the **LLM gateway** falls back DeepSeek → MiniMax with zero code change; **12+ media engines** plug in behind one router; everything lands on a **dual-driver** (SQLite ⇄ PostgreSQL) platform. One line of text is refined stage-by-stage ( ); every artifact is persisted to the dual-driver DB + asset store and is independently reusable, so any stage can

be re-run in isolation. *(Animation renders on GitHub; the ModelScope mirror shows static PNG. 473** (13 releases, 2026-09-30 → 10-09). One pattern ran through most of them: **settings that looked like they worked but had no code reading them**, and **engine requests that looked like they succeeded but sent the wrong thing**. 467 only full-film generation read the project's aspect ratio. Regenerating a single shot, self-healing retakes, segment retake, 4K re-render, recomposing after a

chat edit, scene-image regeneration and the ad workshop each fell back to their own 16:9 or 9:16, so a 9:16 project could get a landscape shot back. They now all read through **one shared parser**. Prompt templates no longer hard-code (a vertical project used to send Midjourney both and ); Midjourney parameters are moved to the end and appear once, and non-Midjourney image engines and the video engines receive plain text. 35:1, which no

video engine we ship can output; the ad workshop's aspect is now selectable and defaults to the project's. **Settings that finally have a reader** *(v12. The short-video planner dropped the resolution / frame-rate / upscaling / interpolation / motion-strength controls that nothing read (the defaults claimed 8K, 4× upscale and interpolation), and its aspect choice now carries over to the create page. 6 m, then aim at subjects : it tilts 19° down and the console now calls it a high-angle

shot. The 3D view, the flat preview, the prompt line and the layout sketch all use this one camera. Same camera, flat preview: the horizon sits high in the frame because the lens points down. 465 a raised camera still looked level, while the prompt already said "high angle". **Engine requests that were silently wrong** *(v12. 20 while the official schema is a string, so **every MiniMax generation with reference images was rejected (2013) and quietly fell back to another

engine**; a live call found it. The Vidu host default existed twice, one copy wrong; Midjourney prompts carried duplicated and