Seedance 2.5: FLF2V is a first–last frame to video workflow that generates a smooth, locked-endpoint transition between two user-provided images. It uses two LoadImage nodes to bring in your start and end frames, then passes them to ByteDance2FirstLastFrameNode, which calls the Seedance 2.5 model to synthesize the in-between motion and appearance changes while preserving both endpoints. Finally, SaveVideo encodes the returned frame sequence into a playable video file.

Technically, the ByteDance2FirstLastFrameNode estimates a coherent motion path and visual evolution between the first and last frames so the video “lands” exactly on your inputs. This makes it ideal for creating believable camera moves, time-of-day shifts, or scene population changes without re-shooting. Because endpoints are locked, the output is especially stable for shot bridges, storyboard previz, and before–after showcases. SaveVideo then packages the generated frames at your chosen playback rate for quick review or handoff.