One MiniMax H3 generation = a 12.25 s multi-shot video: 4-5 shots with hard cuts, up to 3 characters and lip-synced dialogue, rendered in ONE pass so faces, room and lighting stay consistent across cuts. Runs on a 16 GB GPU.<ul><li>ComfyUI workflow (API format), core H3 nodes only (Reference-to-Video, 3 references at full size)</li><li>Structured multi-shot prompt template + a complete real example</li><li>Post-processing scripts: GPEN face restoration with temporal smoothing, and RIFE 48 fps with scene-cut detection (no ghost frames on cuts)</li><li>README with the editing rules that fixed lip sync, eyelines and teeth</li></ul>Full method: <a href="https://civarchive.com/articles/38455" rel="ugc">Multi-shot AI videos in one 12-second generation</a>. Adults only: every character is generated and age-checked.

MiniMax H3 Multi-Shot Storyboard Workflow (Ref2VA, 16GB)

Workflow .json unchanged from v1.2. This update is about the writing rules and the optional post-processing script.<ul><li>Adaptive face restore (optional script): stronger blend on full-frame faces, following your own setting. Measured on one close-up shot: about x2.6 more apparent detail instead of x1.6, but more flicker (+18 % frame-to-frame change instead of +10 %); lower FACE_FORCE if it bothers you.</li><li>One shared description for the reference still and <code>subject_definitions</code> (her face changed between cuts when they disagreed; small sample so far).</li><li>Avoid on-screen text: H3 garbles writing, so inserts show the object and a voice says the content. Template updated.</li><li>Strict timing rules written out, and how to fix an overflowing line.</li></ul>Core ComfyUI nodes only, nothing to install; the .py files are optional and run outside ComfyUI (see the README FAQ).

Files with SHA256: 7b0095c7325007f19ca935a07d14fe34e16fd21810d6e1fa024eda22e0fd713d