This ComfyUI workflow builds a clean background plate by removing an object from video using SAM3-driven masks and a mask-conditioned LTX-2.3 In‑Outpainting IC‑LoRA. The pipeline loads your clip with VHS_LoadVideo/VHS_VideoInfo, extracts frames via GetVideoComponents, and uses LoadSAM3Model → SAM3VideoSegmentation to seed a mask for the object you want to remove. SAM3Propagate tracks that mask across the shot, and SAM3VideoOutput provides a per‑frame OBJECT_MASK. To ensure seamless fills, LTXVDilateVideoMask expands the mask (e.g., s10/t1) and GrowMaskWithBlur feathers the edges.

The masked region is then green‑filled by LTXVInpaintPreprocess, and CreateVideo re‑encodes those preprocessed frames. That green plate, together with the OBJECT_MASK and your minimal background‑only prompt, feeds the LTX 2.3 In‑Outpainting IC‑LoRA (packaged here as a subgraph node), which is explicitly mask‑conditioned to generate only inside the masked area. Utility nodes like VHS_GetImageCount, ComfyMathExpression, and GetImageRangeFromBatch let you preview limited frame ranges before a full run. Finally, SaveVideo writes the cleanplate result for downstream compositing.

FAQ

Frequently Asked Questions

View all workflows
Character
Cinematic
Image to Video
Lip Sync
Multiple Angles
Portrait
Style Reference
Style Transfer
Text to Video
Video Generation
Video
Showing 30 of 577 templates