LTX-2.5(專業版):圖像轉影片

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.

Input

The first frame of the video.

Describe what happens, how the camera moves and the sound.

Length of the video.

Fast is quicker and cheaper; Pro gives higher quality.

Output size; pick the orientation that matches the start image.

Advanced settings

Frames per second.

Adds sound generated with the video.

Leave empty for a new result each run. Enter a number to repeat one.

Output
00:00
Example

試試範例

關於此工作流程

這個 ComfyUI 工作流程可將單一參考影像轉換為電影感多鏡頭影片,採用 LTX-2.5 快速精煉模型。流程串接三個節點:LoadImage 載入來源靜態圖,LtxApi25ImageToVideo 將該圖傳送至 LTX-2.5 API 進行動作合成與鏡頭生成,SaveVideo 將回傳片段寫入磁碟。LTX-2.5 支援原生多鏡頭生成與自動長度預測,讓結果更像短片段而非單一平移或縮放。

技術上,LtxApi25ImageToVideo 節點會將所有鏡頭條件設定於同一張輸入圖,有助於多鏡頭間保持角色、光線與風格一致。節點負責與遠端服務溝通、排隊生成並輸出可儲存影片。SaveVideo 會以你選定的檔名與幀率編碼結果。此流程特別適合快速分鏡、社群貼文與預視:只需一張乾淨參考圖,API 會自動推斷節奏與運鏡,幾分鐘內即可匯出連貫多鏡頭片段。

問答