Masked video inpainting on Wan 2.2 VACE. You paint the subject on a single frame and MatAnyone propagates that mask across the whole clip, with matting quality edges on fine detail like hair. How it works This runs twice. The first run stops at a preview so you paint the mask on frame zero. The second run propagates it and renders. If you want text prompted masking with no painting and a single pass, use the <a rel="ugc" href="https://civarchive.com/models/2876173/wan-22-vace-video-inpaint-sam3-text-prompt-masking-int8-convrot">SAM3 version</a> instead. Painted masking is slower to set up, but it gives you exact control over what is covered, and MatAnyone handles soft edges better than a detector can. Features INT8 ConvRot models throughout, native on Ampere and newer, no FP8 emulation Chunked sampling loop, so clip length is not bounded by VRAM Optional 4x upscale with per source type model recommendations Runs on 4 step Lightning distills, a few seconds per chunk rather than minutes Full on canvas documentation covering every knob and all download links

Wan 2.2 VACE Video Inpaint: MatAnyone Painted Masking (INT8 ConvRot)

First public release. Painted masked video inpainting on Wan 2.2 Fun VACE. Paint the subject on one frame, MatAnyone propagates it across the clip with matting quality edges on fine detail like hair. Runs twice: the first pass stops so you paint, the second renders. Runs on INT8 ConvRot models and 4 step Lightning distills.

Files with SHA256: 12e69595ccf6d38b6628675c3f7d5e9172be95797a7f79968ea2c2d57562f7c1