Demo — inputs & output
Prompt structure inspired by Inspired by fal.ai H3 Guide
Precision Costume Swap
Swap one garment from reference image onto performer in video — wardrobe fixit edit.
Who this is for
Wardrobe continuity and brand outfit corrections.
How this prompt is built
Read this first — once you see the pattern, you can write your own without starting from zero.
- @image1
Garment lock.
- Constraint
Face and other clothes unchanged.
Adapt it for your project
- Specify which performer in group shots.
- Hat or dress swap variant.
Where people mess up
- Garment slides independently of body.
- Color grade drift on fabric.
Your reference files (what to upload)
| File | Job in the video |
|---|---|
| Image 1 | Target costume reference |
Full prompt (copy & edit)
In the reference video, replace the performer's current jacket with the exact garment from @image1. Preserve face, hair, lighting direction, and all other wardrobe pieces. Match fabric fold behavior during movement.
New to Ref2VA? Read the MiniMax H3 Ref2VA prompt guide
Related prompts
Cat-to-Dog Replacement
Video editing with one-line substitution prompt
Prompt structure
Replace the cat in the video with a dog. Keep everything else in the shot stable: background, c…
Day-to-Night Relighting
Single-video relight instruction
Prompt structure
Change the lighting in the reference video from daytime to night. Preserve all subject motion, …
Multi-Element Scene Editing
Multi-line edit list on one source video
Prompt structure
In the reference video: replace the newspaper with a green hardcover book; replace the chair wi…
Product, Sign & Dialogue Replacement
Complex multi-swap edit on single clip
Prompt structure
In the reference video, replace the canned drink shown at the beginning with Coca-Cola. Change …