- family
- multi-shot
- modality
- text->text(x6 prompts)->image(x6)->video(x6 w/audio)->merged video
- whyMultiModel
- An LLM planning model drives per-shot prompt generation, a separate text-to-image model renders each keyframe, a separate image-to-video model (with native audio generation) animates each shot, and an ffmpeg merge step assembles the final cut, all as one chained endpoint.
- steps
- [object Object], [object Object]
- controls
- film name input; LLM scene planner enforces one clear action per scene and ambient-only audio (no dialogue), sequencing scenes toward a narrative climax; ffmpeg merge stitches final order
- exampleStack
- OpenRouter Gemini 2.5 Flash (scene planner LLM) -> Nano Banana Pro (per-scene text-to-image, x6) -> Seedance 1.5 Pro i2v (per-scene animate+audio, x6) -> fal ffmpeg-api merge-videos
- useCases
[generating short immersive POV trailers/homages to a film's setting][rapid multi-scene sizzle reels from a single text seed][prototyping episodic short-form video from narrative prompts]
- pitfalls
- LLM-authored per-scene prompts can drift in visual continuity between the 6 independently generated keyframes since there is no shared identity/style-lock adapter across scenes; distinct from multi-shot-narrative-stitch (Qwen Image Edit + Wan, per-shot keyframe->i2v->concatenate) and storyboard-grid-to-multishot-video (single Nano Banana 2 storyboard grid then Kling 3.0 multi-shot animate) because here an LLM planner generates independent per-scene prompts and each scene is a separately generated keyframe+clip with native generated audio, not a single grid split into shots
