This workflow turns two still images into a single, fluid video transition using the LTX-2.5 image-to-video API. Two LoadImage nodes supply your start and end reference frames, which are passed into LtxApi25ImageToVideo. The node blends structural cues from both inputs to synthesize an in-between sequence that morphs from the first image toward the second, producing a natural-looking transition, reveal, or morph. Finally, SaveVideo encodes the generated frames to a video file you can review or drop into an edit.

Technically, the LtxApi25ImageToVideo node makes an API call to the LTX-2.5 backend, which analyzes both images, aligns major features, and interpolates motion across a specified duration and frame rate. Because the processing happens remotely, you’ll typically configure an API key/endpoint in the node and choose key parameters like output length and FPS. Keeping both input images similar in aspect ratio, framing, and subject scale helps the model establish a clean “path” between them, reducing artifacts and ensuring a smoother morph. SaveVideo then writes the result to disk at your chosen frame rate, ready for playback or further editing.