返回工作流

Change Any Objects

Use simple prompt to mask out certain objects within a video, and replace the object using prompt, or optional reference image. Model used: SAM3 + WAN 2.1 VACE inpainting

下载工作流在 Cloud 中试用

Input

Name the object in the video, in a word or two (e.g. "lemon").

Default: pineapple

Describe the shot with the new object in it.

A photo of the replacement object, ideally on a plain background.

The clip with the object to replace.

How many frames of the clip to process (89 at 30 fps is about 3 s); keep it 4n+1.

Default: 89

Output height.

Default: 1,280

Output width; 1280×720 for wide, 720×1280 for tall.

Default: 720

Advanced settings

What to avoid.

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

Run

Output
00:00
Example

试试一个示例

关于此工作流

The 'Change Any Objects' workflow in ComfyUI is designed to enable users to seamlessly replace or alter objects within a video using simple text prompts or optional reference images. This workflow leverages advanced inpainting techniques, utilizing models like SAM3 and Wan2.1 VACE, to achieve precise object masking and replacement.

The process begins with loading video inputs and setting up the necessary configurations using nodes like VHS_LoadVideo and WanVideoDecode. The SAM3 model is crucial for video segmentation and object masking, allowing users to specify which objects to alter through intuitive prompts. Once the objects are identified, the Wan2.1 VACE model takes over to inpaint and replace these objects with new content derived from the user's prompts or reference images. This combination of models and nodes provides a powerful tool for video editing, enabling creative transformations without the need for extensive manual editing.

常见问答