LTX-2.5 (Pro): Image to Video
Generate video from a single image using LTX-2.5's fast distilled model, delivering cinematic multi-shot sequences with consistent characters, lighting, and style across cuts. The workflow outputs a video file with native multishot support and automatic duration prediction. Ideal for rapid storyboarding, social media content creation, and pre-visualization in commercial production pipelines.
试试一个示例
关于此工作流
This ComfyUI workflow turns a single reference image into a cinematic, multi-shot video using the LTX-2.5 fast distilled model. It links three nodes end-to-end: LoadImage brings your source still into the graph, LtxApi25ImageToVideo sends that image to the LTX-2.5 API for motion synthesis and shot generation, and SaveVideo writes the returned clip to disk. Because LTX-2.5 supports native multishot generation and automatic duration prediction, the result feels like a short edited sequence rather than a single continuous pan or zoom.
Technically, the LtxApi25ImageToVideo node conditions all shots on the same input frame, which helps maintain character, lighting, and style consistency across cuts. The node handles request/response with the remote service, queues generation, and outputs a ready-to-save video. SaveVideo then encodes the result at your chosen filename and frame rate. This makes the workflow ideal for rapid storyboarding, social posts, and pre-visualization: drop in one clean reference image, let the API infer pacing and camera moves, and export a cohesive multi-shot clip in minutes.
常见问答
LtxApi25ImageToVideo calls a remote service; most deployments require an API key. Your source image and parameters are sent to the provider for generation. Check the node’s credentials field and the provider’s documentation and terms before use.
The node supports native multishot and automatic duration prediction. If your template exposes overrides, you can set a target duration and/or shot count; otherwise, leave auto duration enabled for best pacing.
Use a clean, high-quality image with clear subject separation and coherent lighting. Keep faces unobstructed, avoid heavy motion blur, and compose for the aspect ratio you plan to export (16:9 is a solid default).
All shots are conditioned on the same input image inside the LTX-2.5 model via the LtxApi25ImageToVideo node. This shared conditioning helps preserve character identity, lighting, and overall style from shot to shot.