返回工作流

VOID: Video Inpainting

Upload a video and mask the object you want to remove. Generate a clean video with the object and its physical interactions deleted.

下载工作流在 Cloud 中试用

Input

A short name SAM3 can find in every frame, e.g. dog, person, car.

Default: human

Describe the scene as it should look without the object.

The clip to clean up; the first few seconds are used.

Seconds of video to process.

Processing size; 672×384 is the default.

Processing size; 672×384 is the default.

Advanced settings

How closely to follow the prompt.

Default: 6

Skip the refining second pass: faster, less stable over time.

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

Where to start in the clip.

Default: 0 seconds

Steps for each of the two passes.

Default: 30

Run

Output
00:00
Example

试试一个示例

关于此工作流

This ComfyUI tutorial shows how to remove objects from a video using the VOID: Video Inpainting workflow. The graph is simple and fast to learn: LoadVideo reads your clip, a single VOID inpainting node (c3157b75-484a-459e-b8de-57823bef5130) performs segmentation and temporal inpainting, and SaveVideo writes the cleaned result. A MarkdownNote in the canvas provides inline guidance. Under the hood, segmentation is powered by SAM3 (using the sam3.1_multiplex_fp16.safetensors checkpoint). You can guide what to erase with a text cue encoded by a T5-XXL text encoder, a hand-drawn mask, or both for maximum precision.

Technically, the core VOID node runs a two-pass, temporally-aware inpainting model from the Netflix/void-model project. Pass one removes the masked content per frame and estimates plausible backgrounds; pass two propagates structure over time to reduce flicker and preserve motion parallax. This makes it well-suited for real object removal rather than single-frame patching: reflections, shadows, and brief occlusions are handled more coherently across frames. Because it operates in fp16, it balances quality and speed on modern GPUs while keeping memory use manageable.

常见问答