Everything in the narrated short, but a character from your asset library speaks the hook and the call to action on camera (with its own face and voice), while each beat in between stays a product shot voiced in the same voice, lined up with the beat and captioned, exported as a vertical short with an "AI-generated" label. Pick the character on “Pick the presenter” before running; it needs a front image and a voice in the asset library; real people need a consent declaration, and a cloned voice needs one too. Where a video model is available, the beats in between move, as in the narrated short (the hook and call to action are already presenter video): one more paid video generation per beat, with about (target length minus hook and call to action) ÷ the start node's beat_seconds beats. This copy includes “Put this beat in motion”: the start node's beat_seconds is every beat's length, and the video model you pick has to make that length. Without a video model, open the per-beat loop on the canvas after importing, delete “Put this beat in motion”, “File this beat's clip” and “Mute this beat's clip”, then wire the output of “Paint this beat” into the asset of “Lay it down for this beat's length” — every beat then lays a still for beat_seconds. Or add the template from the in-app gallery: without a video model it is built with stills.
Turn a topic into a creative brief, script and visual bible; characters and locations already in the asset library are reused with their references, and only new ones get a turnaround sheet or concept art — saved to the library — auto-build a 3D blockout with each shot's camera position and move, then generate each shot from a first frame (and a last frame where needed) painted on the blockout — or straight from the turnarounds and the blockout camera move — and assemble, caption and export the video. Each line is voiced by the speaker the storyboard names: a character that carries a voice in the asset library speaks in it, the narrator and characters without one use the start node's voice; with a music model, a background score is generated and laid under the dialogue. Cost: by default up to 8 shots, each one video generation plus one or two keyframe images, on top of up to 7 turnaround and location images (none for those already in the library), 5 chat calls, per-shot voicing and one music track — the most expensive template here; max_shots on the start node caps the shot count, and shot_seconds sets each shot's length (preset to the length the chosen video model can make that is closest to its default).
Shoot one episode of a short drama: the same pipeline as "Topic to finished video" — reuse library characters and locations, storyboard, 3D blockout cameras, per-shot keyframes — but the script and storyboard are driven by dialogue (narration only sets the scene) and dialogue shots face the speaker; the video model speaks each character's line while it generates the shot, so the delivery follows the moment (needs a video model with native voice, such as MiniMax H3); narration is voiced separately. The topic can be a shot-by-shot script (picture, speaker, line). Build the characters and locations with "Series bible" first, then shoot episode by episode. Cost: as "Topic to finished video". This copy includes “Act this line in the character's voice” (a dialogue model taking a first frame and reference audio, e.g. the ComfyUI example “H3 dialogue · character voice”): pick the model there after importing so a character sounds the same across shots. Without such a model, delete “Does the speaking character carry a voice?”, “Record a reference line in this character's voice” and “Act this line in the character's voice”; lines are then spoken from the text alone. In the app this branch is added only when such a model is set up.
The first step of an episodic show: give the title, premise and number of episodes, and list your own characters and locations one per line if you want to (name, role, looks, the voice you want) — anything left out is filled in from the premise. It writes the episode outline and the look, draws a turnaround and picks a voice for each character, paints concept art for each location, saves them all to the asset library and saves the bible as a note. Then shoot each episode with "Topic to finished video": characters and locations are recognised by name, with the same face and the same voice. Cost: one chat call, plus one turnaround per new character and one concept image per new location (none for those already in the library).