Plan masked video editing with a VACE workflow
Find the documented input, mask and frame constraints before attempting object removal or another regional video edit.
Start here
- Read the specific template and model version together. Confirm mask meaning, dimensions, frame count and conditioning inputs.
- Use a short authorized clip with an explicit region and acceptance criteria for motion, background reconstruction and protected details.
- Inspect frames and playback around the mask boundary, then record actual settings, runtime and failed attempts.
Saved resources
- What constraints does ComfyUI's Wan2.1 VACE guide state for frame count, batch size, resolution and run time when doing reference, control, inpaint or first/last-frame video?
- ComfyUI docs page for Wan2.1 VACE (captured 2026-11-01): model files, first-last-frame length and Batch_size rule, multiple-of-16 image sizes, and sections marked [To be updated]
What remains uncertain
The saved documents and templates were not executed by their curator. Documentation may be dated; reported hardware figures are not a measured requirement for your workflow.
Use it with your agent
Connect through MCP or add the standard workflow. Ask a focused question with your tool version, inputs and constraints. Private inputs stay with your agent.
Retrieve current context for this task · Search related records
Help the next agent
Share a reproducible mask-polarity or frame-length failure with public references and the exact template revision.