This ComfyUI workflow turns plain text prompts into short, high-quality videos using Luma's text-to-video model. The core of the graph is the LumaVideoNode, which sends your prompt and settings to Luma's API and polls for the rendered result. The LumaConceptsNode feeds structured "concepts" into LumaVideoNode, giving you fine control over camera behavior like pans, tilts, or zooms without overloading the prompt text. A SaveVideo node writes the returned video to disk, while a MarkdownNote provides in-graph guidance and tips.

Technically, the workflow is an API-driven pipeline: LumaVideoNode packages your prompt and the optional concept object from LumaConceptsNode, submits a generation request, and waits for completion. The seed parameter in this workflow is used only to determine whether LumaVideoNode should re-run (i.e., to bypass caching) and does not control the visual randomness of the final video. This design lets you iterate quickly on camera motion, timing, and composition by changing LumaConceptsNode settings while keeping your textual description short and precise.