One still image → a 12.25 s video with sound (voice, one spoken line, room tone) where the face does not drift. Runs on a 16 GB GPU in 8 steps.The trick: the same still goes into <code>first_frame</code> AND <code>last_frame</code> of MiniMaxH3ImageToVideo. With a first frame only, the face turned into another person around 6-8 s; anchoring both ends pins the identity while the motion in between stays free.<ul><li>2 ComfyUI workflows (API format), core H3 nodes only: POV with one spoken line, and an oral variant</li><li>Canvas sized to the still's aspect ratio (no squashed portraits)</li><li>README with the prompt rules that fixed real defects: locked camera (no push-in), no wide-open mouth, anatomy wording, male fingernails, how to get exactly one spoken line</li><li>Optional post-processing: GPEN face restoration with temporal smoothing, RIFE 48 fps with scene-cut detection</li></ul>Multi-shot version (4-5 cuts, dialogue between characters): <a href="https://civarchive.com/models/3044945" rel="ugc">MiniMax H3 Multi-Shot Storyboard Workflow</a>. Adults only: use generated, clearly mature characters.

MiniMax H3 Identity-Locked Image-to-Video + Audio (FL2VA, 16GB)

v1.1 — fix + clearer README. The workflows themselves are unchanged. Fix in the optional <code>face_restore.py</code> script: it crashed as soon as two faces were tracked at once (a second person, a face on a TV or a poster), and the whole video was then left unrestored.README: new FAQ. You only need the .json (core ComfyUI nodes, nothing to install). “API format” is just ComfyUI's “Export (API)” format: drag it onto the canvas, it is not App mode. The two .py files are optional scripts I run outside ComfyUI after the render; they are not custom nodes and do not go in any ComfyUI folder.

Files with SHA256: a349d690d8f3b95a7906c6a3c73b0a96fda43d94fa034b81ad20bb23b8c21663