ワークフローに戻る

LTX-2 Pose to Video

Generate high-quality videos from pose guidance with synchronized audio-video generation using LTX-2. Features precise pose control, expressive motion, and efficient performance.

ワークフローをダウンロードCloudで試す

Input

The person to animate, full body and facing the camera; it becomes the first frame.

A clip of someone moving; their body pose (DWPose) drives the character. Match the framing of the character image.

Describe the scene, the motion and any sound.

Number of frames to read from the pose video (8n+1, e.g. 97, 121); 121 frames at 24 fps is about 5 seconds.

Default: 121

1280×720 is the default; the model snaps to the nearest size it supports.

1280×720 is the default; the model snaps to the nearest size it supports.

Advanced settings

Frames per second; set it to the pose video's rate.

Default: 24

Don't use the character image as the first frame (the pose still follows the video).

What to avoid.

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

Run

Output
00:00
Example

例を試す

このワークフローについて

The LTX-2 Pose to Video workflow is designed to transform pose guidance into high-quality video content with synchronized audio and video generation. Utilizing the LTX-2 model from Lightricks, this workflow offers precise control over pose and expressive motion, making it ideal for creating dynamic video content.

The workflow integrates various nodes such as GetVideoComponents, PreviewImage, and SaveVideo, which help in breaking down the video into components, previewing frames, and saving the final output, respectively. A key feature of this workflow is its use of the comfyui_controlnet_aux custom nodes, which enhance the precision of pose control and motion expression.

Technically, the workflow begins with video and image preprocessing using nodes like LoadVideo and ResizeImageMaskNode. It then employs the DWPreprocessor for refining video settings, ensuring optimal frame count and resolution. The workflow is designed to handle resolutions up to 1920x1088, though it defaults to 720p for efficiency. The frame count must be divisible by 8 plus 1, ensuring smooth transitions and synchronization.

This workflow is particularly useful for creators seeking to produce videos with detailed motion and synchronized audio, leveraging the power of the LTX-2 model to achieve professional-grade results.

よくある質問