Remove background hiss, transcribe the video with timestamps, identify pauses, fillers and repetition, then create a cut plan and a cleaned video while preserving the original. Suited to talks and interviews up to about 30 minutes; split longer footage first.
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).