Collected sources and patterns will appear here. Add from search or the patterns library.
ShortPrompt -> DenseStructuredPrompt
Expand short scene descriptions into dense, structured, spatial-temporally rich prompts using an LLM prior to video/image generation.
Problem it solves
Short user prompts lack the detail needed to guide multi-second video diffusion models to generate high-fidelity, coherent scenes.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.